Für die volle Funktionalität dieser Site ist JavaScript notwendig. Hier finden Sie eine Anleitung zum Aktivieren von JavaScript in Ihrem Browser.

Publikationen

Institut für Künstliche Intelligenz (KI)

Alle unsere bisherigen Publikationen.

Unsere Publikationen

2026
1. Elshani, D., Hernandez, D., Nakhaee, A., Arrascue, A. A., Staab, S., & Wortmann, T. (2026). geof3D: SPARQL geometric functions for co-designing buildings. Advanced Engineering Informatics, 71, 104261. https://doi.org/10.1016/j.aei.2025.104261
  - BibTeX
  BibTeX
  @article{ELSHANI2026104261, abstract = {Semantic Web technologies are increasingly used in the architecture, engineering, and construction (AEC) industry, yet the Resource Description Framework (RDF) and its query language, SPARQL, still lack native support for 3D geometry. Existing approaches either reduce geometry to 2D, rely on external spatial databases, or require processing workflows outside the semantic layer. This paper introduces geof3D, an extension to SPARQL that enables 3D geometric computation directly inside RDF triple stores. The framework is grounded in a formal function space derived from Architectural Geometry and provides typed operators for measurement, spatial predicates, constructive solid modeling, and affine transformations. These functions are implemented as SPARQL built-ins in RDF4J, supported by an execution backend that uses Java-based processing together with SFCGAL, a robust computational geometry engine accessed through the Java Native Interface (JNI). The system supports operations including geometric validation, Boolean solids, 3D spatial queries, and shape transformations without leaving the RDF environment. We evaluate geof3D using real building models from the Large-Scale Construction Robotics Laboratory and show that the framework supports spatial alignment, clash detection, and algorithmic modeling entirely through RDF-native queries. The evaluation examines both expressiveness and implementation performance, combining in-browser benchmarking with direct JNI measurements and comparative testing against a PostGIS configuration to assess performance, scalability, and geometric fidelity. All code, queries, datasets, and benchmarks are openly released. This work shows that SPARQL can serve not only as a semantic query language but also as a computational interface for 3D co-design, enabling integrated, interoperable, and geometry-aware workflows for building information management.}, author = {Elshani, Diellza and Hernandez, Daniel and Nakhaee, Ali and Arrascue, Anthony A. and Staab, Steffen and Wortmann, Thomas}, doi = {https://doi.org/10.1016/j.aei.2025.104261}, issn = {1474-0346}, journal = {Advanced Engineering Informatics}, pages = 104261, title = {geof3D: SPARQL geometric functions for co-designing buildings}, url = {https://www.sciencedirect.com/science/article/pii/S1474034625011541}, volume = 71, year = 2026 }
2. Elshani, D., Hernandez, D., Nakhaee, A., Arrascue, A. A., Staab, S., & Wortmann, T. (2026). geof3D: SPARQL geometric functions for co-designing buildings. Advanced Engineering Informatics, 71, 104–261. https://doi.org/10.1016/j.aei.2025.104261
  - BibTeX
  BibTeX
  @article{ELSHANI2026104261, abstract = {Semantic Web technologies are increasingly used in the architecture, engineering, and construction (AEC) industry, yet the Resource Description Framework (RDF) and its query language, SPARQL, still lack native support for 3D geometry. Existing approaches either reduce geometry to 2D, rely on external spatial databases, or require processing workflows outside the semantic layer. This paper introduces geof3D, an extension to SPARQL that enables 3D geometric computation directly inside RDF triple stores. The framework is grounded in a formal function space derived from Architectural Geometry and provides typed operators for measurement, spatial predicates, constructive solid modeling, and affine transformations. These functions are implemented as SPARQL built-ins in RDF4J, supported by an execution backend that uses Java-based processing together with SFCGAL, a robust computational geometry engine accessed through the Java Native Interface (JNI). The system supports operations including geometric validation, Boolean solids, 3D spatial queries, and shape transformations without leaving the RDF environment. We evaluate geof3D using real building models from the Large-Scale Construction Robotics Laboratory and show that the framework supports spatial alignment, clash detection, and algorithmic modeling entirely through RDF-native queries. The evaluation examines both expressiveness and implementation performance, combining in-browser benchmarking with direct JNI measurements and comparative testing against a PostGIS configuration to assess performance, scalability, and geometric fidelity. All code, queries, datasets, and benchmarks are openly released. This work shows that SPARQL can serve not only as a semantic query language but also as a computational interface for 3D co-design, enabling integrated, interoperable, and geometry-aware workflows for building information management.}, author = {Elshani, Diellza and Hernandez, Daniel and Nakhaee, Ali and Arrascue, Anthony A. and Staab, Steffen and Wortmann, Thomas}, doi = {https://doi.org/10.1016/j.aei.2025.104261}, issn = {1474-0346}, journal = {Advanced Engineering Informatics}, pages = {104-261}, publisher = {Elservier}, title = {geof3D: SPARQL geometric functions for co-designing buildings}, url = {https://www.sciencedirect.com/science/article/pii/S1474034625011541}, volume = 71, year = 2026 }
2025
1. Fathallah, N., Hernández, D., & Staab, S. (2025). AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code. The 27th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS ’25), 25. https://doi.org/10.1145/3663547.3746360
  - BibTeX
  BibTeX
  @inproceedings{fathallah2025accessguruleveragingllmsdetect, abstract = {The vast majority of Web pages fail to comply with established Web accessibility guidelines, excluding a range of users with diverse abilities from interacting with their content. Making Web pages accessible to all users requires dedicated expertise and additional manual efforts from Web page providers. To lower their efforts and promote inclusiveness, we aim to automatically detect and correct Web accessibility violations in HTML code. While previous work has made progress in detecting certain types of accessibility violations, the problem of automatically detecting and correcting accessibility violations remains an open challenge that we address. We introduce a novel taxonomy classifying Web accessibility violations into three key categories - Syntactic, Semantic, and Layout. This taxonomy provides a structured foundation for developing our detection and correction method and redefining evaluation metrics. We propose a novel method, AccessGuru, which combines existing accessibility testing tools and Large Language Models (LLMs) to detect violations and applies taxonomy-driven prompting strategies to correct all three categories. To evaluate these capabilities, we develop a benchmark of real-world Web accessibility violations. Our benchmark quantifies syntactic and layout compliance and judges semantic accuracy through comparative analysis with human expert corrections. Evaluation against our benchmark shows that AccessGuru achieves up to 84% average violation score decrease, significantly outperforming prior methods that achieve at most 50%.}, archiveprefix = {arXiv}, author = {Fathallah, Nadeen and Hernández, Daniel and Staab, Steffen}, booktitle = {The 27th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS ’25)}, doi = {10.1145/3663547.3746360}, eprint = {2507.19549}, eventdate = {26–29 October, 2025}, language = {en}, month = {10}, pages = 25, primaryclass = {cs.SE}, title = {AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code}, url = {https://doi.org/10.1145/3663547.3746360}, venue = {Denver, CO, USA. ACM, New York, NY, USA}, year = 2025 }
2. Fathallah, N., Hernández, D., & Staab, S. (2025, October). AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code. The 27th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS ’25). https://doi.org/10.1145/3663547.3746360
  - BibTeX
  BibTeX
  @inproceedings{fathallah2025accessguruleveragingllmsdetect, abstract = {The vast majority of Web pages fail to comply with established Web accessibility guidelines, excluding a range of users with diverse abilities from interacting with their content. Making Web pages accessible to all users requires dedicated expertise and additional manual efforts from Web page providers. To lower their efforts and promote inclusiveness, we aim to automatically detect and correct Web accessibility violations in HTML code. While previous work has made progress in detecting certain types of accessibility violations, the problem of automatically detecting and correcting accessibility violations remains an open challenge that we address. We introduce a novel taxonomy classifying Web accessibility violations into three key categories - Syntactic, Semantic, and Layout. This taxonomy provides a structured foundation for developing our detection and correction method and redefining evaluation metrics. We propose a novel method, AccessGuru, which combines existing accessibility testing tools and Large Language Models (LLMs) to detect violations and applies taxonomy-driven prompting strategies to correct all three categories. To evaluate these capabilities, we develop a benchmark of real-world Web accessibility violations. Our benchmark quantifies syntactic and layout compliance and judges semantic accuracy through comparative analysis with human expert corrections. Evaluation against our benchmark shows that AccessGuru achieves up to 84% average violation score decrease, significantly outperforming prior methods that achieve at most 50%.}, archiveprefix = {arXiv}, author = {Fathallah, Nadeen and Hernández, Daniel and Staab, Steffen}, booktitle = {The 27th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS ’25)}, doi = {10.1145/3663547.3746360}, eprint = {2507.19549}, eventdate = {26–29 October, 2025}, language = {en}, month = {10}, primaryclass = {cs.SE}, title = {AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code}, type = {Publication}, url = {https://doi.org/10.1145/3663547.3746360}, venue = {Denver, CO, USA. ACM, New York, NY, USA}, year = 2025 }
3. Mohammed, O., Pan, J., Nayyeri, M., Hernández, D., & Staab, S. (2025, October). Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning. Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025). https://doi.org/10.3233/FAIA251186
  - BibTeX
  BibTeX
  @inproceedings{mohammed2025fullhistorygraphsedgetypedecoupled, abstract = {Modeling evolving interactions among entities is critical in many real-world tasks. For example, predicting driver maneuvers in traffic requires tracking how neighboring vehicles accelerate, brake, and change lanes relative to one another over consecutive frames. Likewise, detecting financial fraud hinges on following the flow of funds through successive transactions as they propagate through the network. Unlike classic time-series forecasting, these settings demand reasoning over who interacts with whom and when, calling for a temporal-graph representation that makes both the relations and their evolution explicit. Existing temporal-graph methods typically use snapshot graphs to encode temporal evolution. We introduce a full-history graph that instantiates one node for every entity at every time step and separates two edge sets: (i) intra-time-step edges that capture relations within a single frame and (ii) inter-time-step edges that connect an entity to itself at consecutive steps. To learn on this graph we design an Edge-Type Decoupled Network (ETDNet) with parallel modules: a graph-attention module aggregates information along intra-time-step edges, a multi-head temporal-attention module attends over an entity's inter-time-step history, and a fusion module combines the two messages after every layer. Evaluated on driver-intention prediction (Waymo) and Bitcoin fraud detection (Elliptic++), ETDNet consistently surpasses strong baselines, lifting Waymo joint accuracy to 75.6\% (vs. 74.1\%) and raising Elliptic++ illicit-class F1 to 88.1\% (vs. 60.4\%). These gains demonstrate the benefit of representing structural and temporal relations as distinct edges in a single graph.}, archiveprefix = {arXiv}, author = {Mohammed, Osama and Pan, Jiaxin and Nayyeri, Mojtaba and Hernández, Daniel and Staab, Steffen}, booktitle = {Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025)}, doi = {10.3233/FAIA251186}, eprint = {2508.03251}, eventdate = {25-30 October}, language = {en}, month = {10}, preprinturl = {https://arxiv.org/abs/2508.03251}, primaryclass = {cs.AI}, title = {Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning}, url = {https://ebooks.iospress.nl/doi/10.3233/FAIA251186}, venue = {Bologna, Italy}, year = 2025 }
4. Mohammed, O., Pan, J., Nayyeri, M., Hernández, D., & Staab, S. (2025, October). Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning. Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025). https://doi.org/10.3233/FAIA251186
  - BibTeX
  BibTeX
  @inproceedings{mohammed2025fullhistorygraphsedgetypedecoupled, abstract = {Modeling evolving interactions among entities is critical in many real-world tasks. For example, predicting driver maneuvers in traffic requires tracking how neighboring vehicles accelerate, brake, and change lanes relative to one another over consecutive frames. Likewise, detecting financial fraud hinges on following the flow of funds through successive transactions as they propagate through the network. Unlike classic time-series forecasting, these settings demand reasoning over who interacts with whom and when, calling for a temporal-graph representation that makes both the relations and their evolution explicit. Existing temporal-graph methods typically use snapshot graphs to encode temporal evolution. We introduce a full-history graph that instantiates one node for every entity at every time step and separates two edge sets: (i) intra-time-step edges that capture relations within a single frame and (ii) inter-time-step edges that connect an entity to itself at consecutive steps. To learn on this graph we design an Edge-Type Decoupled Network (ETDNet) with parallel modules: a graph-attention module aggregates information along intra-time-step edges, a multi-head temporal-attention module attends over an entity's inter-time-step history, and a fusion module combines the two messages after every layer. Evaluated on driver-intention prediction (Waymo) and Bitcoin fraud detection (Elliptic++), ETDNet consistently surpasses strong baselines, lifting Waymo joint accuracy to 75.6\% (vs. 74.1\%) and raising Elliptic++ illicit-class F1 to 88.1\% (vs. 60.4\%). These gains demonstrate the benefit of representing structural and temporal relations as distinct edges in a single graph.}, archiveprefix = {arXiv}, author = {Mohammed, Osama and Pan, Jiaxin and Nayyeri, Mojtaba and Hernández, Daniel and Staab, Steffen}, booktitle = {Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025)}, doi = {10.3233/FAIA251186}, eprint = {2508.03251}, eventdate = {October 25-30}, language = {en}, month = {10}, preprinturl = {https://arxiv.org/abs/2508.03251}, primaryclass = {cs.AI}, title = {Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning}, url = {https://ebooks.iospress.nl/doi/10.3233/FAIA251186}, venue = {Bologna, Italy}, year = 2025 }
5. Sadikaj, Y., Zhou, H., Halilaj, L., Schmid, S., Staab, S., & Plant, C. (2025, October). MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning. Proceedings of the International Conference on Computer Vision, ICCV 2025. https://doi.org/10.48550/arXiv.2504.06740
  - BibTeX
  BibTeX
  @inproceedings{sadikaj2025multiadsdefectawaresupervisionmultitype, abstract = {Precise optical inspection in industrial applications is crucial for minimizing scrap rates and reducing the associated costs. Besides merely detecting if a product is anomalous or not, it is crucial to know the distinct type of defect, such as a bent, cut, or scratch. The ability to recognize the "exact" defect type enables automated treatments of the anomalies in modern production lines. Current methods are limited to solely detecting whether a product is defective or not without providing any insights on the defect type, nevertheless detecting and identifying multiple defects. We propose MultiADS, a zero-shot learning approach, able to perform Multi-type Anomaly Detection and Segmentation. The architecture of MultiADS comprises CLIP and extra linear layers to align the visual- and textual representation in a joint feature space. To the best of our knowledge, our proposal, is the first approach to perform a multi-type anomaly segmentation task in zero-shot learning. Contrary to the other baselines, our approach i) generates specific anomaly masks for each distinct defect type, ii) learns to distinguish defect types, and iii) simultaneously identifies multiple defect types present in an anomalous product. Additionally, our approach outperforms zero/few-shot learning SoTA methods on image-level and pixel-level anomaly detection and segmentation tasks on five commonly used datasets: MVTec-AD, Visa, MPDD, MAD and Real-IAD.}, archiveprefix = {arXiv}, author = {Sadikaj, Ylli and Zhou, Hongkuan and Halilaj, Lavdim and Schmid, Stefan and Staab, Steffen and Plant, Claudia}, booktitle = {Proceedings of the International Conference on Computer Vision, ICCV 2025}, doi = {10.48550/arXiv.2504.06740}, eprint = {2504.06740}, eventdate = {Oct 19 – 23th, 2025}, language = {en}, month = {10}, primaryclass = {cs.CV}, title = {MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning}, url = {https://doi.org/10.48550/arXiv.2504.06740}, venue = {Honolulu, Hawai'i}, year = 2025 }
6. Sadikaj, Y., Zhou, H., Halilaj, L., Schmid, S., Staab, S., & Plant, C. (2025, October). MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning. Proceedings of the International Conference on Computer Vision, ICCV 2025. https://doi.org/10.48550/arXiv.2504.06740
  - BibTeX
  BibTeX
  @inproceedings{sadikaj2025multiadsdefectawaresupervisionmultitype, abstract = {Precise optical inspection in industrial applications is crucial for minimizing scrap rates and reducing the associated costs. Besides merely detecting if a product is anomalous or not, it is crucial to know the distinct type of defect, such as a bent, cut, or scratch. The ability to recognize the "exact" defect type enables automated treatments of the anomalies in modern production lines. Current methods are limited to solely detecting whether a product is defective or not without providing any insights on the defect type, nevertheless detecting and identifying multiple defects. We propose MultiADS, a zero-shot learning approach, able to perform Multi-type Anomaly Detection and Segmentation. The architecture of MultiADS comprises CLIP and extra linear layers to align the visual- and textual representation in a joint feature space. To the best of our knowledge, our proposal, is the first approach to perform a multi-type anomaly segmentation task in zero-shot learning. Contrary to the other baselines, our approach i) generates specific anomaly masks for each distinct defect type, ii) learns to distinguish defect types, and iii) simultaneously identifies multiple defect types present in an anomalous product. Additionally, our approach outperforms zero/few-shot learning SoTA methods on image-level and pixel-level anomaly detection and segmentation tasks on five commonly used datasets: MVTec-AD, Visa, MPDD, MAD and Real-IAD.}, archiveprefix = {arXiv}, author = {Sadikaj, Ylli and Zhou, Hongkuan and Halilaj, Lavdim and Schmid, Stefan and Staab, Steffen and Plant, Claudia}, booktitle = {Proceedings of the International Conference on Computer Vision, ICCV 2025}, doi = {10.48550/arXiv.2504.06740}, eprint = {2504.06740}, eventdate = {Oct 19 – 23th, 2025}, language = {en}, month = {10}, primaryclass = {cs.CV}, title = {MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning}, url = {https://doi.org/10.48550/arXiv.2504.06740}, venue = {Honolulu, Hawai'i}, year = 2025 }
7. Gregucci, C., Xiong, B., Hernandez, D., Loconte, L., Minervini, P., Staab, S., & Vergari, A. (2025, July). Is Complex Query Answering Really Complex? Forty-Second International Conference on Machine Learning.
  - BibTeX
  BibTeX
  @inproceedings{gregucci2025complexqueryansweringreally, abstract = {Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA might not be as complex as we think, as the way they are built distorts our perception of progress in this field. For example, we find that in these benchmarks, most queries (up to 98% for some query types) can be reduced to simpler problems, e.g., link prediction, where only one link needs to be predicted. The performance of state-of-the-art CQA models decreases significantly when such models are evaluated on queries that cannot be reduced to easier types. Thus, we propose a set of more challenging benchmarks composed of queries that require models to reason over multiple hops and better reflect the construction of real-world KGs. In a systematic empirical investigation, the new benchmarks show that current methods leave much to be desired from current CQA methods.}, archiveprefix = {arXiv}, author = {Gregucci, Cosimo and Xiong, Bo and Hernandez, Daniel and Loconte, Lorenzo and Minervini, Pasquale and Staab, Steffen and Vergari, Antonio}, booktitle = {Forty-Second International Conference on Machine Learning}, eprint = {2410.12537}, eventdate = {July 13th - July 19th}, language = {en}, month = {07}, preprinturl = {https://arxiv.org/abs/2410.12537}, primaryclass = {cs.LG}, title = {Is Complex Query Answering Really Complex?}, venue = {Vancouver Convention Center}, year = 2025 }
8. Gregucci, C., Xiong, B., Hernandez, D., Loconte, L., Minervini, P., Staab, S., & Vergari, A. (2025, July). Is Complex Query Answering Really Complex? Forty-Second International Conference on Machine Learning.
  - BibTeX
  BibTeX
  @inproceedings{gregucci2025complexqueryansweringreally, abstract = {Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA might not be as complex as we think, as the way they are built distorts our perception of progress in this field. For example, we find that in these benchmarks, most queries (up to 98% for some query types) can be reduced to simpler problems, e.g., link prediction, where only one link needs to be predicted. The performance of state-of-the-art CQA models decreases significantly when such models are evaluated on queries that cannot be reduced to easier types. Thus, we propose a set of more challenging benchmarks composed of queries that require models to reason over multiple hops and better reflect the construction of real-world KGs. In a systematic empirical investigation, the new benchmarks show that current methods leave much to be desired from current CQA methods.}, archiveprefix = {arXiv}, author = {Gregucci, Cosimo and Xiong, Bo and Hernandez, Daniel and Loconte, Lorenzo and Minervini, Pasquale and Staab, Steffen and Vergari, Antonio}, booktitle = {Forty-Second International Conference on Machine Learning}, eprint = {2410.12537}, eventdate = {July 13th - July 19th}, language = {en}, month = {07}, preprinturl = {https://arxiv.org/abs/2410.12537}, primaryclass = {cs.LG}, title = {Is Complex Query Answering Really Complex?}, venue = {Vancouver Convention Center}, year = 2025 }
9. Zhu, Y., Hernández, D., He, Y., Ding, Z., Xiong, B., Kharlamov, E., & Staab, S. (2025). Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings. In W. Che, J. Nabende, E. Shutova, & M. T. Pilehvar (Eds.), Findings of the Association for Computational Linguistics, ACL 2025 (pp. 4145–4167). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.findings-acl.215
  - BibTeX
  BibTeX
  @inproceedings{DBLP:conf/acl/Zhu00DXKS25, abstract = {Uncertainty quantification in Knowledge Graph Embedding (KGE) methods is crucial for ensuring the reliability of downstream applications. A recent work applies conformal prediction to KGE methods, providing uncertainty estimates by generating a set of answers that is guaranteed to include the true answer with a predefined confidence level. However, existing methods provide probabilistic guarantees averaged over a reference set of queries and answers (marginal coverage guarantee). In high-stakes applications such as medical diagnosis, a stronger guarantee is often required: the predicted sets must provide consistent coverage per query (conditional coverage guarantee). We propose CondKGCP, a novel method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets. CondKGCP merges predicates with similar vector representations and augments calibration with rank information. We prove the theoretical guarantees and demonstrate empirical effectiveness of CondKGCP by comprehensive evaluations.}, author = {Zhu, Yuqicheng and Hern{\'{a}}ndez, Daniel and He, Yuan and Ding, Zifeng and Xiong, Bo and Kharlamov, Evgeny and Staab, Steffen}, bibsource = {dblp computer science bibliography, https://dblp.org}, booktitle = {Findings of the Association for Computational Linguistics, {ACL} 2025}, doi = {10.18653/v1/2025.findings-acl.215}, editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher}, eventdate = {July 27 - August 1, 2025}, month = {07}, pages = {4145--4167}, preprinturl = {https://arxiv.org/abs/2505.16877}, publisher = {Association for Computational Linguistics}, title = {Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings}, url = {https://aclanthology.org/2025.findings-acl.215/}, venue = {Vienna, Austria}, year = 2025 }
10. Zhu, Y., Hernández, D., He, Y., Ding, Z., Xiong, B., Kharlamov, E., & Staab, S. (2025). Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings. In W. Che, J. Nabende, E. Shutova, & M. T. Pilehvar (Eds.), Findings of the Association for Computational Linguistics, ACL 2025 (pp. 4145–4167). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.findings-acl.215
  - BibTeX
  BibTeX
  @inproceedings{DBLP:conf/acl/Zhu00DXKS25, abstract = {Uncertainty quantification in Knowledge Graph Embedding (KGE) methods is crucial for ensuring the reliability of downstream applications. A recent work applies conformal prediction to KGE methods, providing uncertainty estimates by generating a set of answers that is guaranteed to include the true answer with a predefined confidence level. However, existing methods provide probabilistic guarantees averaged over a reference set of queries and answers (marginal coverage guarantee). In high-stakes applications such as medical diagnosis, a stronger guarantee is often required: the predicted sets must provide consistent coverage per query (conditional coverage guarantee). We propose CondKGCP, a novel method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets. CondKGCP merges predicates with similar vector representations and augments calibration with rank information. We prove the theoretical guarantees and demonstrate empirical effectiveness of CondKGCP by comprehensive evaluations.}, author = {Zhu, Yuqicheng and Hern{\'{a}}ndez, Daniel and He, Yuan and Ding, Zifeng and Xiong, Bo and Kharlamov, Evgeny and Staab, Steffen}, bibsource = {dblp computer science bibliography, https://dblp.org}, booktitle = {Findings of the Association for Computational Linguistics, {ACL} 2025}, doi = {10.18653/v1/2025.findings-acl.215}, editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher}, eventdate = {July 27 - August 1, 2025}, month = {07}, pages = {4145--4167}, preprinturl = {https://arxiv.org/abs/2505.16877}, publisher = {Association for Computational Linguistics}, title = {Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings}, url = {https://aclanthology.org/2025.findings-acl.215/}, venue = {Vienna, Austria}, year = 2025 }
11. Zhu, Y., Potyka, N., Pan, J., Xiong, B., He, Y., Kharlamov, E., & Staab, S. (2025). Conformalized Answer Set Prediction for Knowledge Graph Embedding. In L. Chiruzzo, A. Ritter, & L. Wang (Eds.), Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) (pp. 731–750). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.naacl-long.32
  - BibTeX
  BibTeX
  @inproceedings{zhu2025conformalized, abstract = {Knowledge graph embeddings (KGE) apply machine learning methods on knowledge graphs (KGs) to provide non-classical reasoning capabilities based on similarities and analogies. The learned KG embeddings are typically used to answer queries by ranking all potential answers, but rankings often lack a meaningful probabilistic interpretation - lower-ranked answers do not necessarily have a lower probability of being true. This limitation makes it difficult to quantify uncertainty of model’s predictions, posing challenges for the application of KGE methods in high-stakes domains like medicine. We address this issue by applying the theory of conformal prediction that allows generating answer sets, which contain the correct answer with probabilistic guarantees. We explain how conformal prediction can be used to generate such answer sets for link prediction tasks. Our empirical evaluation on four benchmark datasets using six representative KGE methods validates that the generated answer sets satisfy the probabilistic guarantees given by the theory of conformal prediction. We also demonstrate that the generated answer sets often have a sensible size and that the size adapts well with respect to the difficulty of the query.}, address = {Albuquerque, New Mexico}, author = {Zhu, Yuqicheng and Potyka, Nico and Pan, Jiarong and Xiong, Bo and He, Yunjie and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)}, doi = {10.18653/v1/2025.naacl-long.32}, editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu}, isbn = {979-8-89176-189-6}, month = {04}, pages = {731--750}, publisher = {Association for Computational Linguistics}, title = {Conformalized Answer Set Prediction for Knowledge Graph Embedding}, url = {https://aclanthology.org/2025.naacl-long.32/}, year = 2025 }
12. Zhu, Y., Potyka, N., Pan, J., Xiong, B., He, Y., Kharlamov, E., & Staab, S. (2025). Conformalized Answer Set Prediction for Knowledge Graph Embedding. In L. Chiruzzo, A. Ritter, & L. Wang (Eds.), Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) (pp. 731–750). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.naacl-long.32
  - BibTeX
  BibTeX
  @inproceedings{zhu2025conformalized, abstract = {Knowledge graph embeddings (KGE) apply machine learning methods on knowledge graphs (KGs) to provide non-classical reasoning capabilities based on similarities and analogies. The learned KG embeddings are typically used to answer queries by ranking all potential answers, but rankings often lack a meaningful probabilistic interpretation - lower-ranked answers do not necessarily have a lower probability of being true. This limitation makes it difficult to quantify uncertainty of model’s predictions, posing challenges for the application of KGE methods in high-stakes domains like medicine. We address this issue by applying the theory of conformal prediction that allows generating answer sets, which contain the correct answer with probabilistic guarantees. We explain how conformal prediction can be used to generate such answer sets for link prediction tasks. Our empirical evaluation on four benchmark datasets using six representative KGE methods validates that the generated answer sets satisfy the probabilistic guarantees given by the theory of conformal prediction. We also demonstrate that the generated answer sets often have a sensible size and that the size adapts well with respect to the difficulty of the query.}, address = {Albuquerque, New Mexico}, author = {Zhu, Yuqicheng and Potyka, Nico and Pan, Jiarong and Xiong, Bo and He, Yunjie and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)}, doi = {10.18653/v1/2025.naacl-long.32}, editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu}, isbn = {979-8-89176-189-6}, month = {04}, pages = {731--750}, publisher = {Association for Computational Linguistics}, title = {Conformalized Answer Set Prediction for Knowledge Graph Embedding}, url = {https://aclanthology.org/2025.naacl-long.32/}, year = 2025 }
13. Blomqvist, E., Garc\’ıa-Castro, R., Hernández, D., Hitzler, P., Lindecrantz, M., & Poveda-Villalón, M. (2025). Proceedings of The 3rd International Workshop on Knowledge Graphs for Sustainability (KG4S 2025) co-located with the 22nd Extended Semantic Web Conference (ESWC 2025) (Vol. 4002). CEUR-WS.org. https://ceur-ws.org/Vol-4002
  - BibTeX
  BibTeX
  @proceedings{2025proceedings, bibsource = {dblp computer science bibliography, https://dblp.org}, editor = {Blomqvist, Eva and Garc{\'{\i}}a{-}Castro, Ra{\'{u}}l and Hern{\'{a}}ndez, Daniel and Hitzler, Pascal and Lindecrantz, Mikael and Poveda{-}Villal{\'{o}}n, Mar{\'{\i}}a}, eventdate = {June 1st, 2025}, publisher = {CEUR-WS.org}, series = {{CEUR} Workshop Proceedings}, title = {Proceedings of The 3rd International Workshop on Knowledge Graphs for Sustainability {(KG4S} 2025) co-located with the 22nd Extended Semantic Web Conference {(ESWC} 2025)}, url = {https://ceur-ws.org/Vol-4002}, urn = {urn:nbn:de:0074-4002-X}, venue = {Portoroz, Slovenia}, volume = 4002, year = 2025 }
14. Blomqvist, E., García-Castro, R., Hernández, D., Hitzler, P., Lindecrantz, M., & Poveda-Villalón, M. (2025). Proceedings of The 3rd International Workshop on Knowledge Graphs for Sustainability (KG4S 2025) co-located with the 22nd Extended Semantic Web Conference (ESWC 2025) (Vol. 4002). CEUR-WS.org. https://ceur-ws.org/Vol-4002
  - BibTeX
  BibTeX
  @proceedings{2025proceedings, bibsource = {dblp computer science bibliography, https://dblp.org}, editor = {Blomqvist, Eva and Garc{\'{i}}a{-}Castro, Ra{\'{u}}l and Hern{\'{a}}ndez, Daniel and Hitzler, Pascal and Lindecrantz, Mikael and Poveda{-}Villal{\'{o}}n, Mar{\'{\i}}a}, eventdate = {June 1st, 2025}, publisher = {CEUR-WS.org}, series = {{CEUR} Workshop Proceedings}, title = {Proceedings of The 3rd International Workshop on Knowledge Graphs for Sustainability {(KG4S} 2025) co-located with the 22nd Extended Semantic Web Conference {(ESWC} 2025)}, url = {https://ceur-ws.org/Vol-4002}, urn = {urn:nbn:de:0074-4002-X}, venue = {Portoroz, Slovenia}, volume = 4002, year = 2025 }
15. Demartini, G., Hose, K., Acosta, M., Palmonari, M., Cheng, G., Skaf-Molli, H., Ferranti, N., Hernández, D., & Hogan, A. (2025). The Semantic Web - ISWC 2024 - 23rd International Semantic Web Conference, Baltimore, MD, USA, November 11-15, 2024, Proceedings, Part III (Vol. 15233). Springer. https://doi.org/10.1007/978-3-031-77847-6
  - BibTeX
  BibTeX
  @proceedings{DBLP:conf/semweb/2024-3, bibsource = {dblp computer science bibliography, https://dblp.org}, doi = {10.1007/978-3-031-77847-6}, editor = {Demartini, Gianluca and Hose, Katja and Acosta, Maribel and Palmonari, Matteo and Cheng, Gong and Skaf{-}Molli, Hala and Ferranti, Nicolas and Hern{\'{a}}ndez, Daniel and Hogan, Aidan}, isbn = {978-3-031-77846-9}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {The Semantic Web - ISWC 2024 - 23rd International Semantic Web Conference, Baltimore, MD, USA, November 11-15, 2024, Proceedings, Part III}, url = {https://doi.org/10.1007/978-3-031-77847-6}, volume = 15233, year = 2025 }
16. Demartini, G., Hose, K., Acosta, M., Palmonari, M., Cheng, G., Skaf-Molli, H., Ferranti, N., Hernández, D., & Hogan, A. (2025). The Semantic Web - ISWC 2024 - 23rd International Semantic Web Conference, Baltimore, MD, USA, November 11-15, 2024, Proceedings, Part I (Vol. 15231). Springer. https://doi.org/10.1007/978-3-031-77844-5
  - BibTeX
  BibTeX
  @proceedings{DBLP:conf/semweb/2024-1, bibsource = {dblp computer science bibliography, https://dblp.org}, doi = {10.1007/978-3-031-77844-5}, editor = {Demartini, Gianluca and Hose, Katja and Acosta, Maribel and Palmonari, Matteo and Cheng, Gong and Skaf{-}Molli, Hala and Ferranti, Nicolas and Hern{\'{a}}ndez, Daniel and Hogan, Aidan}, isbn = {978-3-031-77843-8}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {The Semantic Web - ISWC 2024 - 23rd International Semantic Web Conference, Baltimore, MD, USA, November 11-15, 2024, Proceedings, Part I}, url = {https://doi.org/10.1007/978-3-031-77844-5}, volume = 15231, year = 2025 }
17. Demartini, G., Hose, K., Acosta, M., Palmonari, M., Cheng, G., Skaf-Molli, H., Ferranti, N., Hernández, D., & Hogan, A. (2025). The Semantic Web - ISWC 2024 - 23rd International Semantic Web Conference, Baltimore, MD, USA, November 11-15, 2024, Proceedings, Part II (Vol. 15232). Springer. https://doi.org/10.1007/978-3-031-77850-6
  - BibTeX
  BibTeX
  @proceedings{DBLP:conf/semweb/2024-2, bibsource = {dblp computer science bibliography, https://dblp.org}, doi = {10.1007/978-3-031-77850-6}, editor = {Demartini, Gianluca and Hose, Katja and Acosta, Maribel and Palmonari, Matteo and Cheng, Gong and Skaf{-}Molli, Hala and Ferranti, Nicolas and Hern{\'{a}}ndez, Daniel and Hogan, Aidan}, isbn = {978-3-031-77849-0}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {The Semantic Web - ISWC 2024 - 23rd International Semantic Web Conference, Baltimore, MD, USA, November 11-15, 2024, Proceedings, Part II}, url = {https://doi.org/10.1007/978-3-031-77850-6}, volume = 15232, year = 2025 }
18. Elhalawati, A., Dimou, A., Hartig, O., & Hernández, D. (2025). Flexible RML-Based Mapping of Property Graphs to RDF. In S. Dumbrava & R. Tommasini (eds.), Proceedings of the Workshops of the EDBT/ICDT 2025 Joint Conference (March 25-28, 2025), Barcelona, Spain. CEUR.
  - BibTeX
  BibTeX
  @inproceedings{elhalawati2025flexible, abstract = {RDF graphs and (Labeled) Property Graphs (PGs) have emerged as data models for representing graph databases. Given the differences between the two models, ensuring interoperability between them has become essential, to leverage the strengths of both models. Various approaches have been proposed to map PGs to RDF graphs. However, these approaches differ in terms of structure, representation, size of the generated RDF graph, and degree of configuration provided to the user, making direct comparisons challenging. While declarative methods prevailed to construct RDF graphs from other data formats, the mapping languages proposed for such transformations have not been considered so far for mapping PGs to RDF graphs. In this work, we provide a representation of PG-to-RDF approaches through templates described using RML, a mapping language to construct RDF graphs from heterogeneous data. We show that all considered PG-to-RDF approaches can be represented in RML and, by having a uniform representation of them, we can compare them showcasing their differences. Finally, we show that not only can RML be used to capture PG-to-RDF mappings, but it actually offers more expressive power than the considered PG-to-RDF approaches.}, author = {Elhalawati, Ali and Dimou, Anastasia and Hartig, Olaf and Hernández, Daniel}, booktitle = {Proceedings of the Workshops of the EDBT/ICDT 2025 Joint Conference (March 25-28, 2025), Barcelona, Spain}, editor = {Dumbrava, Stefania and Tommasini, Riccardo}, eventdate = {March 25, 2025}, eventtitle = {Transforming Graph Data Workshop}, language = {English}, publisher = {CEUR}, title = {Flexible RML-Based Mapping of Property Graphs to RDF}, venue = {Barcelona, Spain}, year = 2025 }
19. Elhalawati, A., Dimou, A., Hartig, O., & Hernández, D. (2025). Flexible RML-Based Mapping of Property Graphs to RDF. In S. Dumbrava & R. Tommasini (eds.), Proceedings of the Workshops of the EDBT/ICDT 2025 Joint Conference (March 25-28, 2025), Barcelona, Spain. CEUR.
  - BibTeX
  BibTeX
  @inproceedings{elhalawati2025flexible, abstract = {RDF graphs and (Labeled) Property Graphs (PGs) have emerged as data models for representing graph databases. Given the differences between the two models, ensuring interoperability between them has become essential, to leverage the strengths of both models. Various approaches have been proposed to map PGs to RDF graphs. However, these approaches differ in terms of structure, representation, size of the generated RDF graph, and degree of configuration provided to the user, making direct comparisons challenging. While declarative methods prevailed to construct RDF graphs from other data formats, the mapping languages proposed for such transformations have not been considered so far for mapping PGs to RDF graphs. In this work, we provide a representation of PG-to-RDF approaches through templates described using RML, a mapping language to construct RDF graphs from heterogeneous data. We show that all considered PG-to-RDF approaches can be represented in RML and, by having a uniform representation of them, we can compare them showcasing their differences. Finally, we show that not only can RML be used to capture PG-to-RDF mappings, but it actually offers more expressive power than the considered PG-to-RDF approaches.}, author = {Elhalawati, Ali and Dimou, Anastasia and Hartig, Olaf and Hernández, Daniel}, booktitle = {Proceedings of the Workshops of the EDBT/ICDT 2025 Joint Conference (March 25-28, 2025), Barcelona, Spain}, editor = {Dumbrava, Stefania and Tommasini, Riccardo}, eventdate = {March 25, 2025}, eventtitle = {Transforming Graph Data Workshop}, language = {English}, publisher = {CEUR}, title = {Flexible RML-Based Mapping of Property Graphs to RDF}, venue = {Barcelona, Spain}, year = 2025 }
20. Elshani, D., Lombardi, A., Hernandez, D., Staab, S., Fisher, A., & Wortmann, T. (2025). AEC Co-design workflow for cross-domain querying and reasoning using Semantic Web Technologies. Automation in Construction, 176, 106226. https://doi.org/10.1016/j.autcon.2025.106226
  - BibTeX
  BibTeX
  @article{ELSHANI2025106226, abstract = {The Architecture, Engineering, and Construction (AEC) industry faces data integration challenges due to fragmented silos and diverse data representations, hindering cross-domain queries and early detection of design constraints. Semantic Web Technologies (SWTs) address data integration challenges. This paper evaluates the impact of SWTs on co-design workflows by comparing them with alternative approaches to assess their effectiveness in supporting interdisciplinary collaboration and design constraint detection. Using Design Science Research, a co-design methodology is developed that integrates SWTs with AEC tools for reasoning and federated querying. A component of this methodology is a bidirectional mapping strategy for translating object-oriented data models, demonstrated with the Building Habitat Object Model (BHoM), an AEC interoperability framework. Findings reveal that integrating SWTs enables reasoning and complex queries across federated datasets, improving co-design efficiency. These findings support AEC professionals in advancing co-design and data-driven decision-making, while also informing future research on integrating SWTs into AEC design workflows.}, author = {Elshani, Diellza and Lombardi, Alessio and Hernandez, Daniel and Staab, Steffen and Fisher, Al and Wortmann, Thomas}, doi = {https://doi.org/10.1016/j.autcon.2025.106226}, issn = {0926-5805}, journal = {Automation in Construction}, pages = 106226, title = {AEC Co-design workflow for cross-domain querying and reasoning using Semantic Web Technologies}, url = {https://www.sciencedirect.com/science/article/pii/S0926580525002663}, volume = 176, year = 2025 }
21. Elshani, D., Lombardi, A., Hernandez, D., Staab, S., Fisher, A., & Wortmann, T. (2025). AEC Co-design workflow for cross-domain querying and reasoning using Semantic Web Technologies. Automation in Construction, 176, 106226. https://doi.org/10.1016/j.autcon.2025.106226
  - BibTeX
  BibTeX
  @article{ELSHANI2025106226, abstract = {The Architecture, Engineering, and Construction (AEC) industry faces data integration challenges due to fragmented silos and diverse data representations, hindering cross-domain queries and early detection of design constraints. Semantic Web Technologies (SWTs) address data integration challenges. This paper evaluates the impact of SWTs on co-design workflows by comparing them with alternative approaches to assess their effectiveness in supporting interdisciplinary collaboration and design constraint detection. Using Design Science Research, a co-design methodology is developed that integrates SWTs with AEC tools for reasoning and federated querying. A component of this methodology is a bidirectional mapping strategy for translating object-oriented data models, demonstrated with the Building Habitat Object Model (BHoM), an AEC interoperability framework. Findings reveal that integrating SWTs enables reasoning and complex queries across federated datasets, improving co-design efficiency. These findings support AEC professionals in advancing co-design and data-driven decision-making, while also informing future research on integrating SWTs into AEC design workflows.}, author = {Elshani, Diellza and Lombardi, Alessio and Hernandez, Daniel and Staab, Steffen and Fisher, Al and Wortmann, Thomas}, doi = {https://doi.org/10.1016/j.autcon.2025.106226}, issn = {0926-5805}, journal = {Automation in Construction}, pages = 106226, title = {AEC Co-design workflow for cross-domain querying and reasoning using Semantic Web Technologies}, url = {https://www.sciencedirect.com/science/article/pii/S0926580525002663}, volume = 176, year = 2025 }
22. He, Y., Xiong, B., Hernández, D., Zhu, Y., Kharlamov, E., & Staab, S. (2025). DAGE: DAG Query Answering via Relational Combinator with Logical Constraints. The Web Conference 2025. https://doi.org/10.1145/3696410.3714677
  - BibTeX
  BibTeX
  @inproceedings{he2025dage, abstract = {Predicting answers to queries over knowledge graphs is called a complex reasoning task because answering a query requires subdividing it into subqueries. Existing query embedding methods use this decomposition to compute the embedding of a query as the combination of the embedding of the subqueries. This requirement limits the answerable queries to queries having a single free variable and being decomposable, which are called tree-form queries and correspond to the SROI^- description logic. In this paper, we define a more general set of queries, called DAG queries and formulated in the ALCOIR description logic, propose a query embedding method for them, called DAGE, and a new benchmark to evaluate query embeddings on them. Given the computational graph of a DAG query, DAGE combines the possibly multiple paths between two nodes into a single path with a trainable operator that represents the intersection of relations and learns DAG-DL from tautologies. We show that it is possible to implement DAGE on top of existing query embedding methods, and we empirically measure the improvement of our method over the results of vanilla methods evaluated in tree-form queries that approximate the DAG queries of our proposed benchmark.}, author = {He, Yunjie and Xiong, Bo and Hern{\'a}ndez, Daniel and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {THE WEB CONFERENCE 2025}, doi = {https://doi.org/10.1145/3696410.3714677}, language = {en}, title = {DAGE: DAG Query Answering via Relational Combinator with Logical Constraints}, url = {https://openreview.net/forum?id=x1nXBzUknn}, year = 2025 }
23. He, Y., Xiong, B., Hernández, D., Zhu, Y., Kharlamov, E., & Staab, S. (2025). DAGE: DAG Query Answering via Relational Combinator with Logical Constraints. The Web Conference 2025. https://doi.org/10.1145/3696410.3714677
  - BibTeX
  BibTeX
  @inproceedings{he2025dage, abstract = {Predicting answers to queries over knowledge graphs is called a complex reasoning task because answering a query requires subdividing it into subqueries. Existing query embedding methods use this decomposition to compute the embedding of a query as the combination of the embedding of the subqueries. This requirement limits the answerable queries to queries having a single free variable and being decomposable, which are called tree-form queries and correspond to the SROI^- description logic. In this paper, we define a more general set of queries, called DAG queries and formulated in the ALCOIR description logic, propose a query embedding method for them, called DAGE, and a new benchmark to evaluate query embeddings on them. Given the computational graph of a DAG query, DAGE combines the possibly multiple paths between two nodes into a single path with a trainable operator that represents the intersection of relations and learns DAG-DL from tautologies. We show that it is possible to implement DAGE on top of existing query embedding methods, and we empirically measure the improvement of our method over the results of vanilla methods evaluated in tree-form queries that approximate the DAG queries of our proposed benchmark.}, author = {He, Yunjie and Xiong, Bo and Hern{\'a}ndez, Daniel and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {THE WEB CONFERENCE 2025}, doi = {https://doi.org/10.1145/3696410.3714677}, language = {en}, title = {DAGE: DAG Query Answering via Relational Combinator with Logical Constraints}, url = {https://openreview.net/forum?id=x1nXBzUknn}, year = 2025 }
24. Rotondi, D., Scaparro, F., Blum, H., & Arras, K. O. (2025). FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
  - BibTeX
  BibTeX
  @inproceedings{rotondi2025fungraph, author = {Rotondi, Dennis and Scaparro, Fabio and Blum, Hermann and Arras, Kai O.}, journal = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, title = {FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction}, year = 2025 }
25. Rotondi, D., Scaparro, F., Blum, H., & Arras, K. O. (2025). FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
  - BibTeX
  BibTeX
  @inproceedings{rotondi2025fungraph, author = {Rotondi, Dennis and Scaparro, Fabio and Blum, Hermann and Arras, Kai O.}, journal = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, title = {FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction}, year = 2025 }
26. Thapa, R. B., Hernández, D., Brandt, N., Klein, J.-F., Hoffmann, E., Staab, S., Selzer, M., & Lanza, G. (2025). A Roadmap to Create a Knowledge Graph for the Circular Factory for the Perpetual Product. In E. Blomqvist, R. Garc\’ıa-Castro, D. Hernández, P. Hitzler, M. Lindecrantz, & M. Poveda-Villalón (Eds.), Proceedings of The 3rd International Workshop on Knowledge Graphs for Sustainability (KG4S 2025) co-located with the 22nd Extended Semantic Web Conference (ESWC 2025) (Vol. 4002, pp. 46–52). CEUR-WS.org. https://ceur-ws.org/Vol-4002/short8.pdf
  - BibTeX
  BibTeX
  @inproceedings{thapa2025roadmap, abstract = {New economic systems are needed to decouple resource consumption from wealth. The linear economic approach of “take-make-use-dispose” is not a recipe for success in the long term. Circular production offers a solution to this problem. Our Collaborative Research Center 1574 aims to enable integrated linear and circular production on an industrial scale. To this end, the Collaborative Research Center 1574 investigates how used products and their multiple generations can achieve the vision of the perpetual product. This research involves multiple scientific questions related to production technology, product development and materials technology, ergonomics, robotics, computer science, and knowledge modeling. The Collaborative Research Center 1574 involves eighteen subprojects. Each one studies a dimension of these multiple scientific questions. One of these subprojects, called INF, aims to provide an infrastructure and teach the other subprojects’ researchers how to operate and integrate all the data they produced into a unified knowledge graph. This paper describes the roadmap of the INF subproject, including the ongoing work, future steps, and vision of the INF subproject.}, author = {Thapa, Ratan Bahadur and Hern{\'{a}}ndez, Daniel and Brandt, Nico and Klein, Jan{-}Felix and Hoffmann, Etienne and Staab, Steffen and Selzer, Michael and Lanza, Gisela}, bibsource = {dblp computer science bibliography, https://dblp.org}, booktitle = {Proceedings of The 3rd International Workshop on Knowledge Graphs for Sustainability {(KG4S} 2025) co-located with the 22nd Extended Semantic Web Conference {(ESWC} 2025)}, editor = {Blomqvist, Eva and Garc{\'{\i}}a{-}Castro, Ra{\'{u}}l and Hern{\'{a}}ndez, Daniel and Hitzler, Pascal and Lindecrantz, Mikael and Poveda{-}Villal{\'{o}}n, Mar{\'{\i}}a}, eventdate = {June 1st}, pages = {46--52}, publisher = {CEUR-WS.org}, series = {{CEUR} Workshop Proceedings}, title = {A Roadmap to Create a Knowledge Graph for the Circular Factory for the Perpetual Product}, url = {https://ceur-ws.org/Vol-4002/short8.pdf}, venue = {Portoroz, Slovenia}, volume = 4002, year = 2025 }
27. Thapa, R. B., Hernández, D., Brandt, N., Klein, J.-F., Hoffmann, E., Staab, S., Selzer, M., & Lanza, G. (2025). A Roadmap to Create a Knowledge Graph for the Circular Factory for the Perpetual Product. In E. Blomqvist, R. Garc\’ıa-Castro, D. Hernández, P. Hitzler, M. Lindecrantz, & M. Poveda-Villalón (Eds.), Proceedings of The 3rd International Workshop on Knowledge Graphs for Sustainability (KG4S 2025) co-located with the 22nd Extended Semantic Web Conference (ESWC 2025) (Vol. 4002, pp. 46–52). CEUR-WS.org. https://ceur-ws.org/Vol-4002/short8.pdf
  - BibTeX
  BibTeX
  @inproceedings{thapa2025roadmap, abstract = {New economic systems are needed to decouple resource consumption from wealth. The linear economic approach of “take-make-use-dispose” is not a recipe for success in the long term. Circular production offers a solution to this problem. Our Collaborative Research Center 1574 aims to enable integrated linear and circular production on an industrial scale. To this end, the Collaborative Research Center 1574 investigates how used products and their multiple generations can achieve the vision of the perpetual product. This research involves multiple scientific questions related to production technology, product development and materials technology, ergonomics, robotics, computer science, and knowledge modeling. The Collaborative Research Center 1574 involves eighteen subprojects. Each one studies a dimension of these multiple scientific questions. One of these subprojects, called INF, aims to provide an infrastructure and teach the other subprojects’ researchers how to operate and integrate all the data they produced into a unified knowledge graph. This paper describes the roadmap of the INF subproject, including the ongoing work, future steps, and vision of the INF subproject.}, author = {Thapa, Ratan Bahadur and Hern{\'{a}}ndez, Daniel and Brandt, Nico and Klein, Jan{-}Felix and Hoffmann, Etienne and Staab, Steffen and Selzer, Michael and Lanza, Gisela}, bibsource = {dblp computer science bibliography, https://dblp.org}, booktitle = {Proceedings of The 3rd International Workshop on Knowledge Graphs for Sustainability {(KG4S} 2025) co-located with the 22nd Extended Semantic Web Conference {(ESWC} 2025)}, editor = {Blomqvist, Eva and Garc{\'{\i}}a{-}Castro, Ra{\'{u}}l and Hern{\'{a}}ndez, Daniel and Hitzler, Pascal and Lindecrantz, Mikael and Poveda{-}Villal{\'{o}}n, Mar{\'{\i}}a}, eventdate = {June 1st}, pages = {46--52}, publisher = {CEUR-WS.org}, series = {{CEUR} Workshop Proceedings}, title = {A Roadmap to Create a Knowledge Graph for the Circular Factory for the Perpetual Product}, url = {https://ceur-ws.org/Vol-4002/short8.pdf}, venue = {Portoroz, Slovenia}, volume = 4002, year = 2025 }
28. Zhu, Y., Potyka, N., Hern’andez, D., He, Y., Ding, Z., Xiong, B., Zhou, D., Kharlamov, E., & Staab, S. (2025). ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation. Proceedings of Machine Learning Research in 19th Conference on Neurosymbolic Learning and Reasoning, 284, 1–22. https://arxiv.org/abs/2508.20131
  - BibTeX
  BibTeX
  @inproceedings{zhu2025argrag, abstract = {Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evidence and opaque, stochastic decision-making. We propose ArgRAG, an explainable, and contestable alternative that replaces black-box reasoning with structured inference using a Quantitative Bipolar Argumentation Framework (QBAF). ArgRAG constructs a QBAF from retrieved documents and performs deterministic reasoning under gradual semantics. This allows faithfully explaining and contesting decisions. Evaluated on two fact verification benchmarks, PubHealth and RAGuard, ArgRAG achieves strong accuracy while significantly improving transparency.}, author = {Zhu, Yuqicheng and Potyka, Nico and Hern'andez, Daniel and He, Yuan and Ding, Zifeng and Xiong, Bo and Zhou, Dongzhuoran and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {Proceedings of Machine Learning Research in 19th Conference on Neurosymbolic Learning and Reasoning}, eventdate = {Sep 10}, language = {en}, pages = {1-22}, preprinturl = {https://arxiv.org/abs/2508.20131}, title = {ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation}, url = {https://arxiv.org/abs/2508.20131}, venue = {Santa Cruz, California}, volume = 284, year = 2025 }
29. Zhu, Y., Potyka, N., Hernández, D., He, Y., Ding, Z., Xiong, B., Zhou, D., Kharlamov, E., & Staab, S. (2025). ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation. Proceedings of Machine Learning Research in 19th Conference on Neurosymbolic Learning and Reasoning, 284, 1–22. https://arxiv.org/abs/2508.20131
  - BibTeX
  BibTeX
  @inproceedings{zhu2025argrag, abstract = {Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evidence and opaque, stochastic decision-making. We propose ArgRAG, an explainable, and contestable alternative that replaces black-box reasoning with structured inference using a Quantitative Bipolar Argumentation Framework (QBAF). ArgRAG constructs a QBAF from retrieved documents and performs deterministic reasoning under gradual semantics. This allows faithfully explaining and contesting decisions. Evaluated on two fact verification benchmarks, PubHealth and RAGuard, ArgRAG achieves strong accuracy while significantly improving transparency.}, author = {Zhu, Yuqicheng and Potyka, Nico and Hern{\'{a}}ndez, Daniel and He, Yuan and Ding, Zifeng and Xiong, Bo and Zhou, Dongzhuoran and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {Proceedings of Machine Learning Research in 19th Conference on Neurosymbolic Learning and Reasoning}, eventdate = {Sep 10}, language = {en}, pages = {1-22}, preprinturl = {https://arxiv.org/abs/2508.20131}, title = {ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation}, url = {https://arxiv.org/abs/2508.20131}, venue = {Santa Cruz, California}, volume = 284, year = 2025 }
2024
1. Pan, X., Hernández, D., Seifer, P., Lämmel, R., & Staab, S. (2024). eSPARQL: Representing and Reconciling Agnostic and Atheistic Beliefs in RDF-star Knowledge Graphs. In G. Demartini, K. Hose, M. Acosta, M. Palmonari, G. Cheng, H. Skaf-Molli, N. Ferranti, D. Hernández, & A. Hogan (eds.), The Semantic Web - ISWC 2024 - 23rd International Semantic Web Conference, Baltimore, MD, USA, November 11-15, 2024, Proceedings, Part II (Vol. 15232, pp. 155–172). Springer. https://doi.org/10.1007/978-3-031-77850-6_9
  - BibTeX
  BibTeX
  @inproceedings{pan2024esparqlrepresentingreconcilingagnostic, abstract = {Over the past few years, we have seen the emergence of large knowledge graphs combining information from multiple sources. Sometimes, this information is provided in the form of assertions about other assertions, defining contexts where assertions are valid. A recent extension to RDF which admits statements over statements, called RDF-star, is in revision to become a W3C standard. However, there is no proposal for a semantics of these RDF-star statements nor a built-in facility to operate over them. In this paper, we propose a query language for epistemic RDF-star metadata based on a four-valued logic, called eSPARQL. Our proposed query language extends SPARQL-star, the query language for RDF-star, with a new type of FROM clause to facilitate operating with multiple and sometimes conflicting beliefs. We show that the proposed query language can express four use case queries, including the following features: (i) querying the belief of an individual, (ii) the aggregating of beliefs, (iii) querying who is conflicting with somebody, and (iv) beliefs about beliefs (i.e., nesting of beliefs).}, archiveprefix = {arXiv}, author = {Pan, Xinyi and Hernández, Daniel and Seifer, Philipp and Lämmel, Ralf and Staab, Steffen}, booktitle = {The Semantic Web - ISWC 2024 - 23rd International Semantic Web Conference, Baltimore, MD, USA, November 11-15, 2024, Proceedings, Part II}, doi = {10.1007/978-3-031-77850-6_9}, editor = {Demartini, Gianluca and Hose, Katja and Acosta, Maribel and Palmonari, Matteo and Cheng, Gong and Skaf-Molli, Hala and Ferranti, Nicolas and Hernández, Daniel and Hogan, Aidan}, eprint = {2407.21483}, eventtitle = {23rd International Semantic Web Conference}, language = {English}, month = {11}, pages = {155-172}, preprinturl = {https://arxiv.org/abs/2407.21483}, primaryclass = {cs.AI}, publisher = {Springer}, title = {eSPARQL: Representing and Reconciling Agnostic and Atheistic Beliefs in RDF-star Knowledge Graphs}, url = {https://doi.org/10.1007/978-3-031-77850-6_9}, venue = {Baltimore, MD, USA}, volume = 15232, year = 2024 }
2. He, Y., Hernandez, D., Nayyeri, M., Xiong, B., Zhu, Y., Kharlamov, E., & Staab, S. (2024). Generating SROI⁻ Ontologies via Knowledge Graph Query Embedding Learning. In U. Endriss, F. S. Melo, K. Bach, A. J. Bugarín Diz, J. M. Alonso-Moral, S. Barro, & F. Heintz (eds.), ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain - Including 13th Conference on Prestigious Applications of Intelligent Systems (PAIS 2024) (Vol. 392, pp. 4279–4286). IOS Press. https://doi.org/10.3233/FAIA241002
  - BibTeX
  BibTeX
  @inproceedings{he2024generatingsroiontologiesknowledge, abstract = {Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily rely on excessively parameterized neural networks and cannot explain the knowledge learned from the graph. We propose a novel query embedding method, AConE, which explains the knowledge learned from the graph in the form of SROI− description logic axioms while being more parameter-efficient than most existing approaches. AConE associates queries to SROI− description logic concepts. Every SROI− concept is embedded as a cone in complex vector space, and each SROI− relation is embedded as a transformation that rotates and scales cones. We show theoretically that AConE can learn SROI− axioms, and defines an algebra whose operations correspond one-to-one to SROI− description logic concept constructs. Our empirical study on multiple query datasets shows that AConE achieves superior results over previous baselines with fewer parameters. Notably on the WN18RR dataset, AConE achieves significant improvement over baseline models. We provide comprehensive analyses showing that the capability to represent axioms positively impacts the results of query answering.}, archiveprefix = {arXiv}, author = {He, Yunjie and Hernandez, Daniel and Nayyeri, Mojtaba and Xiong, Bo and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain - Including 13th Conference on Prestigious Applications of Intelligent Systems (PAIS 2024)}, doi = {10.3233/FAIA241002}, editor = {Endriss, Ulle and Melo, Francisco S. and Bach, Kerstin and Bugarín Diz, Alberto José and Alonso-Moral, Jose Maria and Barro, Senén and Heintz, Fredrik}, eprint = {2407.09212}, isbn = {978-1-64368-548-9}, language = {English}, month = {10}, pages = {4279 - 4286}, preprinturl = {https://arxiv.org/abs/2407.09212}, primaryclass = {cs.AI}, publisher = {IOS Press}, series = {Frontiers in Artificial Intelligence and Applications}, title = {Generating SROI⁻ Ontologies via Knowledge Graph Query Embedding Learning}, url = {https://doi.org/10.3233/FAIA241002}, venue = {Santiago de Compostela, Spain}, volume = 392, year = 2024 }
3. He, Y., Hernandez, D., Nayyeri, M., Xiong, B., Zhu, Y., Kharlamov, E., & Staab, S. (2024). Generating SROI- Ontologies via Knowledge Graph Query Embedding Learning. Ecai 2024, 392, 4279–4286. https://doi.org/10.3233/FAIA241002
  - BibTeX
  BibTeX
  @inproceedings{he2024generating, abstract = {Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily rely on excessively parameterized neural networks and cannot explain the knowledge learned from the graph. We propose a novel query embedding method, AConE, which explains the knowledge learned from the graph in the form of SROI− description logic axioms while being more parameter-efficient than most existing approaches. AConE associates queries to SROI− description logic concepts. Every SROI− concept is embedded as a cone in complex vector space, and each SROI− relation is embedded as a transformation that rotates and scales cones. We show theoretically that AConE can learn SROI− axioms, and defines an algebra whose operations correspond one-to-one to SROI− description logic concept constructs. Our empirical study on multiple query datasets shows that AConE achieves superior results over previous baselines with fewer parameters. Notably on the WN18RR dataset, AConE achieves significant improvement over baseline models. We provide comprehensive analyses showing that the capability to represent axioms positively impacts the results of query answering.}, author = {He, Yunjie and Hernandez, Daniel and Nayyeri, Mojtaba and Xiong, Bo and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {ECAI 2024}, doi = {10.3233/FAIA241002}, isbn = {9781643685489}, issn = {1879-8314}, language = {en}, month = {10}, pages = {4279 - 4286}, preprinturl = {https://arxiv.org/abs/2407.09212}, publisher = {IOS Press}, title = {Generating SROI- Ontologies via Knowledge Graph Query Embedding Learning}, type = {Publication}, url = {https://doi.org/10.3233/FAIA241002}, volume = 392, year = 2024 }
4. He, Y., Hernandez, D., Nayyeri, M., Xiong, B., Zhu, Y., Kharlamov, E., & Staab, S. (2024). Generating SROI- Ontologies via Knowledge Graph Query Embedding Learning. Ecai 2024, 392, 4279–4286. https://doi.org/10.3233/FAIA241002
  - BibTeX
  BibTeX
  @inproceedings{he2024generating, abstract = {Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily rely on excessively parameterized neural networks and cannot explain the knowledge learned from the graph. We propose a novel query embedding method, AConE, which explains the knowledge learned from the graph in the form of SROI− description logic axioms while being more parameter-efficient than most existing approaches. AConE associates queries to SROI− description logic concepts. Every SROI− concept is embedded as a cone in complex vector space, and each SROI− relation is embedded as a transformation that rotates and scales cones. We show theoretically that AConE can learn SROI− axioms, and defines an algebra whose operations correspond one-to-one to SROI− description logic concept constructs. Our empirical study on multiple query datasets shows that AConE achieves superior results over previous baselines with fewer parameters. Notably on the WN18RR dataset, AConE achieves significant improvement over baseline models. We provide comprehensive analyses showing that the capability to represent axioms positively impacts the results of query answering.}, author = {He, Yunjie and Hernandez, Daniel and Nayyeri, Mojtaba and Xiong, Bo and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {ECAI 2024}, doi = {10.3233/FAIA241002}, isbn = {9781643685489}, issn = {1879-8314}, language = {en}, month = {10}, pages = {4279 - 4286}, preprinturl = {https://arxiv.org/abs/2407.09212}, publisher = {IOS Press}, title = {Generating SROI- Ontologies via Knowledge Graph Query Embedding Learning}, type = {Publication}, url = {https://doi.org/10.3233/FAIA241002}, volume = 392, year = 2024 }
5. Navigli, R., Lo Pinto, M., Silvestri, P., Rotondi, D., Ciciliano, S., & Scirè, A. (2024). NounAtlas: Filling the Gap in Nominal Semantic Role Labeling. In L.-W. Ku, A. Martins, & V. Srikumar (Eds.), Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 16245–16258). Association for Computational Linguistics. https://aclanthology.org/2024.acl-long.857
  - BibTeX
  BibTeX
  @inproceedings{navigli-etal-2024-nounatlas, abstract = {Despite significant advances in Semantic Role Labeling (SRL), much work in this field has been carried out with a focus on verbal predicates, with the research on nominal SRL lagging behind. In many contexts, however, nominal predicates are often as informative as verbal ones, thus needing proper treatment. In this paper we aim to fill this gap and make nominal SRL a first-class citizen. We introduce a novel approach to create the first large-scale, high-quality inventory of nominal predicates and organize them into semantically-coherent frames. Although automatically created, NounAtlas {--} our frame inventory {--} is subsequently fully validated. We then put forward a technique to generate silver training data for nominal SRL and show that a state-of-the-art SRL model can achieve good performance. Interestingly, thanks to our design choices which enable seamless integration of our predicate inventory with its verbal counterpart, we can mix verbal and nominal data and perform robust SRL on both types of predicates.}, address = {Bangkok, Thailand}, author = {Navigli, Roberto and Lo Pinto, Marco and Silvestri, Pasquale and Rotondi, Dennis and Ciciliano, Simone and Scir{\`e}, Alessandro}, booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek}, month = {08}, pages = {16245--16258}, publisher = {Association for Computational Linguistics}, title = {NounAtlas: Filling the Gap in Nominal Semantic Role Labeling}, url = {https://aclanthology.org/2024.acl-long.857}, year = 2024 }
6. Navigli, R., Lo Pinto, M., Silvestri, P., Rotondi, D., Ciciliano, S., & Scirè, A. (2024). NounAtlas: Filling the Gap in Nominal Semantic Role Labeling. In L.-W. Ku, A. Martins, & V. Srikumar (Eds.), Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 16245–16258). Association for Computational Linguistics. https://aclanthology.org/2024.acl-long.857
  - BibTeX
  BibTeX
  @inproceedings{navigli-etal-2024-nounatlas, abstract = {Despite significant advances in Semantic Role Labeling (SRL), much work in this field has been carried out with a focus on verbal predicates, with the research on nominal SRL lagging behind. In many contexts, however, nominal predicates are often as informative as verbal ones, thus needing proper treatment. In this paper we aim to fill this gap and make nominal SRL a first-class citizen. We introduce a novel approach to create the first large-scale, high-quality inventory of nominal predicates and organize them into semantically-coherent frames. Although automatically created, NounAtlas {--} our frame inventory {--} is subsequently fully validated. We then put forward a technique to generate silver training data for nominal SRL and show that a state-of-the-art SRL model can achieve good performance. Interestingly, thanks to our design choices which enable seamless integration of our predicate inventory with its verbal counterpart, we can mix verbal and nominal data and perform robust SRL on both types of predicates.}, address = {Bangkok, Thailand}, author = {Navigli, Roberto and Lo Pinto, Marco and Silvestri, Pasquale and Rotondi, Dennis and Ciciliano, Simone and Scir{\`e}, Alessandro}, booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek}, month = {08}, pages = {16245--16258}, publisher = {Association for Computational Linguistics}, title = {NounAtlas: Filling the Gap in Nominal Semantic Role Labeling}, url = {https://aclanthology.org/2024.acl-long.857}, year = 2024 }
7. Seifer, P., Hernández, D., Lämmel, R., & Staab, S. (2024). Inferring SHACL Constraints for Results of Composable Graph Queries (Extended Abstract). In L. Giordano, J. C. Jung, & A. Ozaki (Eds.), Proceedings of the 37th International Workshop on Description Logics (DL 2024), Bergen, Norway, June 18-21, 2024 (Vol. 3739). CEUR-WS.org. https://ceur-ws.org/Vol-3739/abstract-23.pdf
  - BibTeX
  BibTeX
  @inproceedings{DBLP:conf/dlog/Seifer0LS24, abstract = {SPARQL CONSTRUCT queries allow for the specification of data processing pipelines that transform given input graphs into new output graphs. Input graphs are now commonly constrained through SHACL shapes allowing for both their validation and aiding users (as well as tools) in understanding their structure. However, it becomes challenging to understand what graph data can be expected at the end of a data processing pipeline without knowing the particular input data: Shape constraints on the input graph may affect the output graph, but may no longer apply literally, and new shapes may be imposed by the query itself. In our recent work, From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries, we studied the derivation of shape constraints that hold on all possible output graphs of a given SPARQL CONSTRUCT query by axiomatizing the query and the shapes with the ALCHOI description logic. This extended abstract summarizes our previous work.}, author = {Seifer, Philipp and Hern{\'{a}}ndez, Daniel and L{\"{a}}mmel, Ralf and Staab, Steffen}, bibsource = {dblp computer science bibliography, https://dblp.org}, booktitle = {Proceedings of the 37th International Workshop on Description Logics (DL 2024), Bergen, Norway, June 18-21, 2024}, editor = {Giordano, Laura and Jung, Jean Christoph and Ozaki, Ana}, month = {06}, publisher = {CEUR-WS.org}, series = {{CEUR} Workshop Proceedings}, title = {Inferring {SHACL} Constraints for Results of Composable Graph Queries (Extended Abstract)}, url = {https://ceur-ws.org/Vol-3739/abstract-23.pdf}, volume = 3739, year = 2024 }
8. Seifer, P., Hernández, D., Lämmel, R., & Staab, S. (2024). Inferring SHACL Constraints for Results of Composable Graph Queries (Extended Abstract). In L. Giordano, J. C. Jung, & A. Ozaki (Eds.), Proceedings of the 37th International Workshop on Description Logics (DL 2024), Bergen, Norway, June 18-21, 2024 (Vol. 3739). CEUR-WS.org. https://ceur-ws.org/Vol-3739/abstract-23.pdf
  - BibTeX
  BibTeX
  @inproceedings{DBLP:conf/dlog/Seifer0LS24, abstract = {SPARQL CONSTRUCT queries allow for the specification of data processing pipelines that transform given input graphs into new output graphs. Input graphs are now commonly constrained through SHACL shapes allowing for both their validation and aiding users (as well as tools) in understanding their structure. However, it becomes challenging to understand what graph data can be expected at the end of a data processing pipeline without knowing the particular input data: Shape constraints on the input graph may affect the output graph, but may no longer apply literally, and new shapes may be imposed by the query itself. In our recent work, From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries, we studied the derivation of shape constraints that hold on all possible output graphs of a given SPARQL CONSTRUCT query by axiomatizing the query and the shapes with the ALCHOI description logic. This extended abstract summarizes our previous work.}, author = {Seifer, Philipp and Hern{\'{a}}ndez, Daniel and L{\"{a}}mmel, Ralf and Staab, Steffen}, bibsource = {dblp computer science bibliography, https://dblp.org}, booktitle = {Proceedings of the 37th International Workshop on Description Logics (DL 2024), Bergen, Norway, June 18-21, 2024}, editor = {Giordano, Laura and Jung, Jean Christoph and Ozaki, Ana}, month = {06}, publisher = {CEUR-WS.org}, series = {{CEUR} Workshop Proceedings}, title = {Inferring {SHACL} Constraints for Results of Composable Graph Queries (Extended Abstract)}, url = {https://ceur-ws.org/Vol-3739/abstract-23.pdf}, volume = 3739, year = 2024 }
9. Asma, Z., Hernández, D., Galárraga, L., Flouris, G., Fundulaki, I., & Hose, K. (2024, May). NPCS: Native Provenance Computation for SPARQL. Proceedings of the ACM Web Conference 2024 (WWW ’24), May13--17, 2024, Singapore, Singapore. https://doi.org/10.1145/3589334.3645557
  - BibTeX
  BibTeX
  @inproceedings{zubaria2024native, abstract = {The popularity of Knowledge Graphs (KGs) both in industry and academia owes credit to their flexible data model, suitable for data integration from multiple sources. Several KG-based applications such as trust assessment or view maintenance on dynamic data rely on the ability to compute provenance explanations for query results. The how-provenance of a query result is an expression that encodes the records (triples or facts) that explain its inclusion in the result set. This article proposes NPCS, a Native Provenance Computation approach for SPARQL queries. NPCS annotates query results with their how-provenance. By building upon spm-provenance semirings, NPCS supports both monotonic and non-monotonic SPARQL queries. Thanks to its reliance on query rewriting techniques, the approach is directly applicable to already deployed SPARQL engines using different reification schemes -- including RDF-star. Our experimental evaluation on two popular SPARQL engines (GraphDB and Stardog) shows that our novel query rewriting brings a significant runtime improvement over existing query rewriting solutions, scaling to RDF graphs with billions of triples.}, author = {Asma, Zubaria and Hernández, Daniel and Galárraga, Luis and Flouris, Giorgos and Fundulaki, Irini and Hose, Katja}, booktitle = {Proceedings of the ACM Web Conference 2024 (WWW '24), May13--17, 2024, Singapore, Singapore}, doi = {10.1145/3589334.3645557}, eventdate = {May 13 -17 2024}, eventtitle = {WWW '24}, isbn = {979-8-4007-0171-9/24/05}, language = {English}, month = {05}, publisher = {ACM}, title = {NPCS: Native Provenance Computation for SPARQL}, url = {https://doi.org/10.1145/3589334.3645557}, venue = {Singapore}, year = 2024 }
10. Asma, Z., Hernández, D., Galárraga, L., Flouris, G., Fundulaki, I., & Hose, K. (2024, May). NPCS: Native Provenance Computation for SPARQL. Proceedings of the ACM Web Conference 2024 (WWW ’24), May13--17, 2024, Singapore, Singapore. https://doi.org/10.1145/3589334.3645557
  - BibTeX
  BibTeX
  @inproceedings{zubaria2024native, abstract = {The popularity of Knowledge Graphs (KGs) both in industry and academia owes credit to their flexible data model, suitable for data integration from multiple sources. Several KG-based applications such as trust assessment or view maintenance on dynamic data rely on the ability to compute provenance explanations for query results. The how-provenance of a query result is an expression that encodes the records (triples or facts) that explain its inclusion in the result set. This article proposes NPCS, a Native Provenance Computation approach for SPARQL queries. NPCS annotates query results with their how-provenance. By building upon spm-provenance semirings, NPCS supports both monotonic and non-monotonic SPARQL queries. Thanks to its reliance on query rewriting techniques, the approach is directly applicable to already deployed SPARQL engines using different reification schemes -- including RDF-star. Our experimental evaluation on two popular SPARQL engines (GraphDB and Stardog) shows that our novel query rewriting brings a significant runtime improvement over existing query rewriting solutions, scaling to RDF graphs with billions of triples.}, author = {Asma, Zubaria and Hernández, Daniel and Galárraga, Luis and Flouris, Giorgos and Fundulaki, Irini and Hose, Katja}, booktitle = {Proceedings of the ACM Web Conference 2024 (WWW '24), May13--17, 2024, Singapore, Singapore}, doi = {10.1145/3589334.3645557}, eventdate = {May 13 -17 2024}, eventtitle = {WWW '24}, isbn = {979-8-4007-0171-9/24/05}, language = {English}, month = {05}, publisher = {ACM}, title = {NPCS: Native Provenance Computation for SPARQL}, url = {https://doi.org/10.1145/3589334.3645557}, venue = {Singapore}, year = 2024 }
11. Blomqvist, E., García-Castro, R., Hernández, D., Hitzler, P., Lindecrantz, M., & Poveda-Villalón, M. (2024). Proceedings of the The 2nd International Workshop on Knowledge Graphs for Sustainability (KG4S 2024) colocated with the 21st Extended Semantic Web Conference (ESWC 2024) (Vol. 3753). CEUR. https://ceur-ws.org/Vol-3753/
  - BibTeX
  BibTeX
  @proceedings{blomqvist2024proceedings, editor = {Blomqvist, Eva and García-Castro, Raúl and Hernández, Daniel and Hitzler, Pascal and Lindecrantz, Mikael and Poveda-Villalón, María}, eventdate = {2024-05-27}, eventtitle = {Knowledge Graphs for Sustainability 2024}, month = {05}, publisher = {CEUR}, title = {Proceedings of the The 2nd International Workshop on Knowledge Graphs for Sustainability (KG4S 2024) colocated with the 21st Extended Semantic Web Conference (ESWC 2024)}, url = {https://ceur-ws.org/Vol-3753/}, venue = {Hersonissos, Greece, May 27th, 2024}, volume = 3753, year = 2024 }
12. Blomqvist, E., García-Castro, R., Hernández, D., Hitzler, P., Lindecrantz, M., & Poveda-Villalón, M. (2024). Proceedings of the The 2nd International Workshop on Knowledge Graphs for Sustainability (KG4S 2024) colocated with the 21st Extended Semantic Web Conference (ESWC 2024) (Vol. 3753). CEUR. https://ceur-ws.org/Vol-3753/
  - BibTeX
  BibTeX
  @proceedings{blomqvist2024proceedings, editor = {Blomqvist, Eva and García-Castro, Raúl and Hernández, Daniel and Hitzler, Pascal and Lindecrantz, Mikael and Poveda-Villalón, María}, eventdate = {2024-05-27}, eventtitle = {Knowledge Graphs for Sustainability 2024}, month = {05}, publisher = {CEUR}, title = {Proceedings of the The 2nd International Workshop on Knowledge Graphs for Sustainability (KG4S 2024) colocated with the 21st Extended Semantic Web Conference (ESWC 2024)}, url = {https://ceur-ws.org/Vol-3753/}, venue = {Hersonissos, Greece, May 27th, 2024}, volume = 3753, year = 2024 }
13. Elenter, J., Chamon, L. F. O., & Ribeiro, A. (2024, May). Near-Optimal Solutions of Constrained Learning Problems. Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria. https://doi.org/10.48550/arXiv.2403.11844
  - BibTeX
  BibTeX
  @inproceedings{elenter2024nearoptimal, abstract = {With the widespread adoption of machine learning systems, the need to curtail their behavior has become increasingly apparent. This is evidenced by recent advancements towards developing models that satisfy robustness, safety, and fairness requirements. These requirements can be imposed (with generalization guarantees) by formulating constrained learning problems that can then be tackled by dual ascent algorithms. Yet, though these algorithms converge in objective value, even in non-convex settings, they cannot guarantee that their outcome is feasible. Doing so requires randomizing over all iterates, which is impractical in virtually any modern applications. Still, final iterates have been observed to perform well in practice. In this work, we address this gap between theory and practice by characterizing the constraint violation of Lagrangian minimizers associated with optimal dual variables, despite lack of convexity. To do this, we leverage the fact that non-convex, finite-dimensional constrained learning problems can be seen as parametrizations of convex, functional problems. Our results show that rich parametrizations effectively mitigate the issue of feasibility in dual methods, shedding light on prior empirical successes of dual learning. We illustrate our findings in fair learning tasks.}, archiveprefix = {arXiv}, author = {Elenter, Juan and Chamon, Luiz F. O. and Ribeiro, Alejandro}, booktitle = {Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria}, doi = {10.48550/arXiv.2403.11844}, eprint = {2403.11844}, language = {en}, month = {05}, preprinturl = {https://arxiv.org/abs/2403.11844}, primaryclass = {cs.LG}, publisher = {ICLR}, title = {Near-Optimal Solutions of Constrained Learning Problems}, year = 2024 }
14. Elenter, J., Chamon, L. F. O., & Ribeiro, A. (2024, May). Near-Optimal Solutions of Constrained Learning Problems. Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria. https://doi.org/10.48550/arXiv.2403.11844
  - BibTeX
  BibTeX
  @inproceedings{elenter2024nearoptimal, abstract = {With the widespread adoption of machine learning systems, the need to curtail their behavior has become increasingly apparent. This is evidenced by recent advancements towards developing models that satisfy robustness, safety, and fairness requirements. These requirements can be imposed (with generalization guarantees) by formulating constrained learning problems that can then be tackled by dual ascent algorithms. Yet, though these algorithms converge in objective value, even in non-convex settings, they cannot guarantee that their outcome is feasible. Doing so requires randomizing over all iterates, which is impractical in virtually any modern applications. Still, final iterates have been observed to perform well in practice. In this work, we address this gap between theory and practice by characterizing the constraint violation of Lagrangian minimizers associated with optimal dual variables, despite lack of convexity. To do this, we leverage the fact that non-convex, finite-dimensional constrained learning problems can be seen as parametrizations of convex, functional problems. Our results show that rich parametrizations effectively mitigate the issue of feasibility in dual methods, shedding light on prior empirical successes of dual learning. We illustrate our findings in fair learning tasks.}, archiveprefix = {arXiv}, author = {Elenter, Juan and Chamon, Luiz F. O. and Ribeiro, Alejandro}, booktitle = {Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria}, doi = {10.48550/arXiv.2403.11844}, eprint = {2403.11844}, month = {05}, preprinturl = {https://arxiv.org/abs/2403.11844}, primaryclass = {cs.LG}, publisher = {ICLR}, title = {Near-Optimal Solutions of Constrained Learning Problems}, year = 2024 }
15. Elshani, D., Dervishaj, A., Hernández, D., Gudmundsson, K., Staab, S., & Wortmann, T. (2024). An Ontology for the Reuse and Tracking of Prefabricated Building Components. Proceedings of the the 2nd International Workshop on Knowledge Graphs for Sustainability (KG4S 2024) Colocated with the 21st Extended Semantic Web Conference (ESWC 2024), 3753, 53–64. https://ceur-ws.org/Vol-3753/paper5.pdf
  - BibTeX
  BibTeX
  @inproceedings{elshani2024ontology, author = {Elshani, Diellza and Dervishaj, Arlind and Hernández, Daniel and Gudmundsson, Kjartan and Staab, Steffen and Wortmann, Thomas}, booktitle = {Proceedings of the The 2nd International Workshop on Knowledge Graphs for Sustainability (KG4S 2024) colocated with the 21st Extended Semantic Web Conference (ESWC 2024)}, eventdate = {2024-05-27}, eventtitle = {Knowledge Graphs for Sustainability 2024}, month = {05}, pages = {53-64}, publisher = {CEUR}, title = {An Ontology for the Reuse and Tracking of Prefabricated Building Components}, url = {https://ceur-ws.org/Vol-3753/paper5.pdf}, venue = {Hersonissos, Greece, May 27th, 2024}, volume = 3753, year = 2024 }
16. Elshani, D., Dervishaj, A., Hernández, D., Gudmundsson, K., Staab, S., & Wortmann, T. (2024). An Ontology for the Reuse and Tracking of Prefabricated Building Components. Proceedings of the the 2nd International Workshop on Knowledge Graphs for Sustainability (KG4S 2024) Colocated with the 21st Extended Semantic Web Conference (ESWC 2024), 3753, 53–64. https://ceur-ws.org/Vol-3753/paper5.pdf
  - BibTeX
  BibTeX
  @inproceedings{elshani2024ontology, author = {Elshani, Diellza and Dervishaj, Arlind and Hernández, Daniel and Gudmundsson, Kjartan and Staab, Steffen and Wortmann, Thomas}, booktitle = {Proceedings of the The 2nd International Workshop on Knowledge Graphs for Sustainability (KG4S 2024) colocated with the 21st Extended Semantic Web Conference (ESWC 2024)}, eventdate = {2024-05-27}, eventtitle = {Knowledge Graphs for Sustainability 2024}, month = {05}, pages = {53-64}, publisher = {CEUR}, title = {An Ontology for the Reuse and Tracking of Prefabricated Building Components}, url = {https://ceur-ws.org/Vol-3753/paper5.pdf}, venue = {Hersonissos, Greece, May 27th, 2024}, volume = 3753, year = 2024 }
17. Errica, F., & Niepert, M. (2024, May). Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks. Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria. https://doi.org/10.48550/arXiv.2305.10544
  - BibTeX
  BibTeX
  @inproceedings{errica2024tractable, abstract = {We introduce Graph-Induced Sum-Product Networks (GSPNs), a new probabilistic framework for graph representation learning that can tractably answer probabilistic queries. Inspired by the computational trees induced by vertices in the context of message-passing neural networks, we build hierarchies of sum-product networks (SPNs) where the parameters of a parent SPN are learnable transformations of the a-posterior mixing probabilities of its children's sum units. Due to weight sharing and the tree-shaped computation graphs of GSPNs, we obtain the efficiency and efficacy of deep graph networks with the additional advantages of a probabilistic model. We show the model's competitiveness on scarce supervision scenarios, under missing data, and for graph classification in comparison to popular neural models. We complement the experiments with qualitative analyses on hyper-parameters and the model's ability to answer probabilistic queries.}, archiveprefix = {arXiv}, author = {Errica, Federico and Niepert, Mathias}, booktitle = {Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria}, doi = {10.48550/arXiv.2305.10544}, eprint = {2305.10544}, language = {en}, month = {05}, preprinturl = {https://arxiv.org/abs/2305.10544v2}, primaryclass = {cs.LG}, title = {Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks}, year = 2024 }
18. Errica, F., & Niepert, M. (2024, May). Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks. Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria. https://doi.org/10.48550/arXiv.2305.10544
  - BibTeX
  BibTeX
  @inproceedings{errica2024tractable, abstract = {We introduce Graph-Induced Sum-Product Networks (GSPNs), a new probabilistic framework for graph representation learning that can tractably answer probabilistic queries. Inspired by the computational trees induced by vertices in the context of message-passing neural networks, we build hierarchies of sum-product networks (SPNs) where the parameters of a parent SPN are learnable transformations of the a-posterior mixing probabilities of its children's sum units. Due to weight sharing and the tree-shaped computation graphs of GSPNs, we obtain the efficiency and efficacy of deep graph networks with the additional advantages of a probabilistic model. We show the model's competitiveness on scarce supervision scenarios, under missing data, and for graph classification in comparison to popular neural models. We complement the experiments with qualitative analyses on hyper-parameters and the model's ability to answer probabilistic queries.}, archiveprefix = {arXiv}, author = {Errica, Federico and Niepert, Mathias}, booktitle = {Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria}, doi = {10.48550/arXiv.2305.10544}, eprint = {2305.10544}, language = {en}, month = {05}, preprinturl = {https://arxiv.org/abs/2305.10544v2}, primaryclass = {cs.LG}, publisher = {ICLR}, title = {Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks}, year = 2024 }
19. Hagnberger, J., Kalimuthu, M., Musekamp, D., & Niepert, M. (2024, May). Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent PDEs. Proceedings of the AI4DifferentialEquations in Science Workshop at ICLR 2024, May 7-11, 2024, Austria.
  - BibTeX
  BibTeX
  @inproceedings{hagnberger2024vectorized, abstract = {Neural Operators are a recent class of data-driven models for learning solutions to Partial Differential Equations (PDEs). Traditionally, these models are trained in an autoregressive fashion using data collected at discrete time points in the evolution of the PDE. This setup gives rise to two problems: (i) poor temporal generalization due to error accumulation and (ii) poor zero-shot super-resolution capabilities. To address these issues, we propose Vectorized Conditional Neural Fields (VCNeF), a general framework that utilizes transformers and implicit neural representations to efficiently solve time-dependent PDEs of varying coefficients. A comprehensive evaluation of VCNeF on the challenging 1D and 2D PDEs from PDEBench demonstrates the superiority of our model over four state-of-the-art baselines. Furthermore, our proposed model achieves faster inference and generalizes better to unseen PDE parameters than the compared models.}, author = {Hagnberger, Jan and Kalimuthu, Marimuthu and Musekamp, Daniel and Niepert, Mathias}, booktitle = {Proceedings of the AI4DifferentialEquations in Science workshop at ICLR 2024, May 7-11, 2024, Austria}, month = {05}, publisher = {ICLR}, title = {Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent PDEs}, year = 2024 }

Publikationen

Unsere Publikationen

2026

BibTeX

BibTeX

2025

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

2024

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

So erreichen Sie uns

Zielgruppe

Formalia

Services

Organisation