Publikationen

Institut für Künstliche Intelligenz (KI)

Alle unsere bisherigen Publikationen.

true" ? copyright : '' }

Unsere Publikationen

2025
1. 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 }
2. 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 }
3. 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 }
4. 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 }
5. 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 }
6. 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://openreview.net/forum?id=x1nXBzUknn
  - 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}, language = {en}, preprinturl = {https://doi.org/10.48550/arXiv.2410.22105}, title = {DAGE: DAG Query Answering via Relational Combinator with Logical Constraints}, url = {https://openreview.net/forum?id=x1nXBzUknn}, year = 2025 }
7. 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://openreview.net/forum?id=x1nXBzUknn
  - 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}, language = {en}, preprinturl = {https://doi.org/10.48550/arXiv.2410.22105}, title = {DAGE: DAG Query Answering via Relational Combinator with Logical Constraints}, url = {https://openreview.net/forum?id=x1nXBzUknn}, 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 }
20. 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, 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 }
21. Liu, A., Niepert, M., & den Broeck, G. V. (2024, May). Image Inpainting via Tractable Steering of Diffusion Models. Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7--11, 2024, Austria. https://doi.org/10.48550/arXiv.2401.03349
  - BibTeX
  BibTeX
  @inproceedings{liu2023image, abstract = {Diffusion models are the current state of the art for generating photorealistic images. However, controlling the sampling process for constrained image generation tasks such as inpainting remains challenging since exact conditioning on such constraints is intractable. While existing methods use various techniques to approximate the constrained posterior, this paper proposes to exploit the ability of Tractable Probabilistic Models (TPMs) to exactly and efficiently compute the constrained posterior, and to leverage this signal to steer the denoising process of diffusion models. Specifically, this paper adopts a class of expressive TPMs termed Probabilistic Circuits (PCs). Building upon prior advances, we further scale up PCs and make them capable of guiding the image generation process of diffusion models. Empirical results suggest that our approach can consistently improve the overall quality and semantic coherence of in painted images across three natural image datasets (i.e., CelebA-HQ, ImageNet, and LSUN) with only ~10% additional computational overhead brought by the TPM.}, archiveprefix = {arXiv}, author = {Liu, Anji and Niepert, Mathias and den Broeck, Guy Van}, booktitle = {Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7--11, 2024, Austria}, doi = {10.48550/arXiv.2401.03349}, eprint = {2401.03349}, language = {en}, month = {05}, preprinturl = {https://arxiv.org/abs/2401.03349v1}, primaryclass = {cs.CV}, publisher = {ICLR}, title = {Image Inpainting via Tractable Steering of Diffusion Models}, venue = {Austria}, year = 2024 }
22. Liu, A., Niepert, M., & den Broeck, G. V. (2024, May). Image Inpainting via Tractable Steering of Diffusion Models. Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria. https://doi.org/10.48550/arXiv.2401.03349
  - BibTeX
  BibTeX
  @inproceedings{liu2023image, abstract = {Diffusion models are the current state of the art for generating photorealistic images. However, controlling the sampling process for constrained image generation tasks such as inpainting remains challenging since exact conditioning on such constraints is intractable. While existing methods use various techniques to approximate the constrained posterior, this paper proposes to exploit the ability of Tractable Probabilistic Models (TPMs) to exactly and efficiently compute the constrained posterior, and to leverage this signal to steer the denoising process of diffusion models. Specifically, this paper adopts a class of expressive TPMs termed Probabilistic Circuits (PCs). Building upon prior advances, we further scale up PCs and make them capable of guiding the image generation process of diffusion models. Empirical results suggest that our approach can consistently improve the overall quality and semantic coherence of in painted images across three natural image datasets (i.e., CelebA-HQ, ImageNet, and LSUN) with only ~10% additional computational overhead brought by the TPM.}, archiveprefix = {arXiv}, author = {Liu, Anji and Niepert, Mathias and den Broeck, Guy Van}, booktitle = {Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria}, doi = {10.48550/arXiv.2401.03349}, eprint = {2401.03349}, language = {en}, month = {05}, preprinturl = {https://arxiv.org/abs/2401.03349v1}, primaryclass = {cs.CV}, publisher = {ICLR}, title = {Image Inpainting via Tractable Steering of Diffusion Models}, venue = {Austria}, year = 2024 }
23. Qian, C., Manolache, A., Ahmed, K., Zeng, Z., den Broeck, G. V., Niepert, M., & Morris, C. (2024, May). Probabilistically Rewired Message-Passing Neural Networks. Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7--11, 2024, Austria. https://doi.org/10.48550/arXiv.2310.02156
  - BibTeX
  BibTeX
  @inproceedings{qian2023probabilistically, abstract = {Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input. However, they operate on a fixed input graph structure, ignoring potential noise and missing information. Furthermore, their local aggregation mechanism can lead to problems such as over-squashing and limited expressive power in capturing relevant graph structures. Existing solutions to these challenges have primarily relied on heuristic methods, often disregarding the underlying data distribution. Hence, devising principled approaches for learning to infer graph structures relevant to the given prediction task remains an open challenge. In this work, leveraging recent progress in exact and differentiable k-subset sampling, we devise probabilistically rewired MPNNs (PR-MPNNs), which learn to add relevant edges while omitting less beneficial ones. For the first time, our theoretical analysis explores how PR-MPNNs enhance expressive power, and we identify precise conditions under which they outperform purely randomized approaches. Empirically, we demonstrate that our approach effectively mitigates issues like over-squashing and under-reaching. In addition, on established real-world datasets, our method exhibits competitive or superior predictive performance compared to traditional MPNN models and recent graph transformer architectures.}, archiveprefix = {arXiv}, author = {Qian, Chendi and Manolache, Andrei and Ahmed, Kareem and Zeng, Zhe and den Broeck, Guy Van and Niepert, Mathias and Morris, Christopher}, booktitle = {Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7--11, 2024, Austria}, doi = {10.48550/arXiv.2310.02156}, eprint = {2310.02156}, language = {en}, month = {05}, preprinturl = {https://arxiv.org/abs/2310.02156}, primaryclass = {cs.LG}, publisher = {ICLR}, title = {Probabilistically Rewired Message-Passing Neural Networks}, year = 2024 }
24. Qian, C., Manolache, A., Ahmed, K., Zeng, Z., den Broeck, G. V., Niepert, M., & Morris, C. (2024, May). Probabilistically Rewired Message-Passing Neural Networks. Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria. https://doi.org/10.48550/arXiv.2310.02156
  - BibTeX
  BibTeX
  @inproceedings{qian2023probabilistically, abstract = {Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input. However, they operate on a fixed input graph structure, ignoring potential noise and missing information. Furthermore, their local aggregation mechanism can lead to problems such as over-squashing and limited expressive power in capturing relevant graph structures. Existing solutions to these challenges have primarily relied on heuristic methods, often disregarding the underlying data distribution. Hence, devising principled approaches for learning to infer graph structures relevant to the given prediction task remains an open challenge. In this work, leveraging recent progress in exact and differentiable k-subset sampling, we devise probabilistically rewired MPNNs (PR-MPNNs), which learn to add relevant edges while omitting less beneficial ones. For the first time, our theoretical analysis explores how PR-MPNNs enhance expressive power, and we identify precise conditions under which they outperform purely randomized approaches. Empirically, we demonstrate that our approach effectively mitigates issues like over-squashing and under-reaching. In addition, on established real-world datasets, our method exhibits competitive or superior predictive performance compared to traditional MPNN models and recent graph transformer architectures.}, archiveprefix = {arXiv}, author = {Qian, Chendi and Manolache, Andrei and Ahmed, Kareem and Zeng, Zhe and den Broeck, Guy Van and Niepert, Mathias and Morris, Christopher}, booktitle = {Proceedings of the International Conference on Learning Representations(ICLR 2024), May 7-11, 2024, Austria}, doi = {10.48550/arXiv.2310.02156}, eprint = {2310.02156}, language = {en}, month = {05}, preprinturl = {https://arxiv.org/abs/2310.02156}, primaryclass = {cs.LG}, publisher = {ICLR}, title = {Probabilistically Rewired Message-Passing Neural Networks}, year = 2024 }
25. Seifer, P., Hernández, D., Lämmel, R., & Staab, S. (2024, May). From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries. Proceedings of the ACM Web Conference 2024 (WWW ’24), May13--17, 2024, Singapore, Singapore. https://doi.org/10.1145/3589334.3645550
  - BibTeX
  BibTeX
  @inproceedings{seifer2024shapes, abstract = {SPARQL CONSTRUCT queries allow for the specification of data processing pipelines that transform given input graphs into new output graphs. It is now common to constrain graphs through SHACL shapes allowing users to understand which data they can expect and which not. 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 template. In this paper, we study the derivation of shape constraints that hold on all possible output graphs of a given SPARQL CONSTRUCT query. We assume that the SPARQL CONSTRUCT query is fixed, e.g., being part of a program, whereas the input graphs adhere to input shape constraints but may otherwise vary over time and, thus, are mostly unknown. We study a fragment of SPARQL CONSTRUCT queries (SCCQ) and a fragment of SHACL (Simple SHACL). We formally define the problem of deriving the most restrictive set of Simple SHACL shapes that constrain the results from evaluating a SCCQ over any input graph restricted by a given set of Simple SHACL shapes. We propose and implement an algorithm that statically analyses input SHACL shapes and CONSTRUCT queries and prove its soundness and complexity.}, author = {Seifer, Philipp and Hernández, Daniel and Lämmel, Ralf and Staab, Steffen}, booktitle = {Proceedings of the ACM Web Conference 2024 (WWW '24), May13--17, 2024, Singapore, Singapore}, doi = {10.1145/3589334.3645550}, eventdate = {May 13–17, 2024}, eventtitle = {WWW '24}, isbn = {979-8-4007-0171-9/24/05}, month = {05}, preprinturl = {https://arxiv.org/abs/2402.08509}, publisher = {ACM}, title = {From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries}, url = {https://doi.org/10.1145/3589334.3645550}, venue = {Singapore}, year = 2024 }
26. Seifer, P., Hernández, D., Lämmel, R., & Staab, S. (2024, May). From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries. Proceedings of the ACM Web Conference 2024 (WWW ’24), May13--17, 2024, Singapore, Singapore. https://doi.org/10.1145/3589334.3645550
  - BibTeX
  BibTeX
  @inproceedings{seifer2024shapes, abstract = {SPARQL CONSTRUCT queries allow for the specification of data processing pipelines that transform given input graphs into new output graphs. It is now common to constrain graphs through SHACL shapes allowing users to understand which data they can expect and which not. 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 template. In this paper, we study the derivation of shape constraints that hold on all possible output graphs of a given SPARQL CONSTRUCT query. We assume that the SPARQL CONSTRUCT query is fixed, e.g., being part of a program, whereas the input graphs adhere to input shape constraints but may otherwise vary over time and, thus, are mostly unknown. We study a fragment of SPARQL CONSTRUCT queries (SCCQ) and a fragment of SHACL (Simple SHACL). We formally define the problem of deriving the most restrictive set of Simple SHACL shapes that constrain the results from evaluating a SCCQ over any input graph restricted by a given set of Simple SHACL shapes. We propose and implement an algorithm that statically analyses input SHACL shapes and CONSTRUCT queries and prove its soundness and complexity.}, author = {Seifer, Philipp and Hernández, Daniel and Lämmel, Ralf and Staab, Steffen}, booktitle = {Proceedings of the ACM Web Conference 2024 (WWW '24), May13--17, 2024, Singapore, Singapore}, doi = {10.1145/3589334.3645550}, eventdate = {May 13–17, 2024}, eventtitle = {WWW '24}, isbn = {979-8-4007-0171-9/24/05}, month = {05}, preprinturl = {https://arxiv.org/abs/2402.08509}, publisher = {ACM}, title = {From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries}, url = {https://doi.org/10.1145/3589334.3645550}, venue = {Singapore}, year = 2024 }
27. Tran, H.-C., Nguyen, D. M. H., Nguyen, M.-D., Le, N. H., & T. Nguyen, B. (2024, May). Energy Minimizing-based Token Merging for Accelerating Transformers. Proceedings of Practical ML for Low Resource Settings in Science Workshop at ICLR 2024, May 7-11, 2024, Austria.
  - BibTeX
  BibTeX
  @inproceedings{tran2024energy, abstract = {Model compression has been an active research field that has been used to reduce the size and complexity of the model. In a recent noteworthy study, ToMe and its variants utilize the Bipartite Soft Matching (BSM) algorithm in which tokens representing patches in an image are split into two sets, and top-k similar tokens from one set are merged. This approach utilizes pre-trained weights, enhances speed, and reduces memory usage. However, these algorithms have some drawbacks. First, the choice of a token-splitting strategy significantly influences algorithm performance since tokens in one set can only perceive tokens in the other set, leading to mis-merging issues. Furthermore, although ToMe is effective in the initial layers, it becomes increasingly problematic in deeper layers as the number of tokens diminishes because of damaged informative tokens. To address these limitations, rather than relying on specific splitting strategies like BSM, we propose a new algorithm called PiToMe. Specifically, we prioritize the protection of informative tokens using an additional factor called energy score. In experiments, PiToMe achieved up to a 50% memory reduction while exhibiting superior off-the-shelf performance on image classification ( keeping a 1.71% average performance drop compared to 2.6% for ToMe) and image-text retrieval (1.35% average performance drop compared to 6.89% for ToMe) compared to previous BSM-based approaches dependent solely on token similarity.}, author = {Tran, Hoai-Chau and Nguyen, Duy Minh Ho and Nguyen, Manh-Duy and Le, Ngan Hoang and T. Nguyen, Binh}, booktitle = {Proceedings of Practical ML for Low Resource Settings in Science workshop at ICLR 2024, May 7-11, 2024, Austria}, language = {en}, month = {05}, publisher = {ICLR}, title = {Energy Minimizing-based Token Merging for Accelerating Transformers}, year = 2024 }
28. Tran, H.-C., Nguyen, D. M. H., Nguyen, M.-D., Le, N. H., & T. Nguyen, B. (2024, May). Energy Minimizing-based Token Merging for Accelerating Transformers. Proceedings of Practical ML for Low Resource Settings in Science Workshop at ICLR 2024, May 7-11, 2024, Austria.
  - BibTeX
  BibTeX
  @inproceedings{tran2024energy, author = {Tran, Hoai-Chau and Nguyen, Duy Minh Ho and Nguyen, Manh-Duy and Le, Ngan Hoang and T. Nguyen, Binh}, booktitle = {Proceedings of Practical ML for Low Resource Settings in Science workshop at ICLR 2024, May 7-11, 2024, Austria}, language = {en}, month = {05}, publisher = {ICLR}, title = {Energy Minimizing-based Token Merging for Accelerating Transformers}, year = 2024 }
29. Zubaria, A., 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
  @conference{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*. 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 = {Zubaria, Asma 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}, 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 }
30. Zubaria, A., 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*. 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 = {Zubaria, Asma 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 }
31. Zubaria, A., 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 = {Zubaria, Asma 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 }
32. “Hosseini, A. S., & “Staab, S. (2024). Disambiguating Emotional Connotations of Words Using Contextualized Word Representations.
  - BibTeX
  BibTeX
  @inproceedings{hosseini2024disambiguating, author = {"Hosseini, Akram Sadat" and "Staab, Steffen"}, title = {Disambiguating Emotional Connotations of Words Using Contextualized Word Representations}, year = 2024 }
33. “Hosseini, A. S., & “Staab, S. (2024). Disambiguating Emotional Connotations of Words Using Contextualized Word Representations. https://doi.org/10.18653/v1/2024.starsem-1.21
  - BibTeX
  BibTeX
  @inproceedings{hosseini2024disambiguating, abstract = {Understanding emotional nuances in written content is crucial for effective communication; however, the context-dependent nature of language poses challenges in precisely discerning emotions in text. This study contributes to the understanding of how the emotional connotations of a word are influenced by the sentence context in which it appears. Leveraging the contextual understanding embedded in contextualized word representations, we conduct an empirical investigation to (i) evaluate the varying abilities of these representations in distinguishing the diverse emotional connotations evoked by the same word across different contexts, (ii) explore potential biases in these representations toward specific emotions of a word, and (iii) assess the capability of these representations in estimating the number of emotional connotations evoked by a word in diverse contexts. Our experiments, utilizing four popular models—BERT, RoBERTa, XLNet, and GPT-2—and drawing on the GoEmotions and SemEval 2018 datasets, demonstrate that these models effectively discern emotional connotations of words. RoBERTa, in particular, shows superior performance and greater resilience against biases. Our further analysis reveals that disambiguating the emotional connotations of words significantly enhances emotion identification at the sentence level.}, author = {"Hosseini, Akram Sadat" and "Staab, Steffen"}, doi = {https://doi.org/10.18653/v1/2024.starsem-1.21}, title = {Disambiguating Emotional Connotations of Words Using Contextualized Word Representations}, url = {https://aclanthology.org/2024.starsem-1.21/}, venue = {Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)}, year = 2024 }
34. Asma, Z., Hernandez, D., Galárraga, L., Flouris, G., Fundulaki, I., & Hose, K. (2024). Code and benchmark for NPCS, a Native Provenance Computation for SPARQL. https://doi.org/10.18419/darus-3973
  - BibTeX
  BibTeX
  @misc{asma2024benchmark, abstract = {Code for the implementation and benchmark of NPCS, a Native Provenance Computation for SPARQL.The code in this dataset includes the implementation of the NPCS system, which is a middleware for SPARQL endpoints that rewrites queries to queries that annotate answers with provenance polynomials (i.e., how-provenance data). The translation rules implemented for the query rewriting can be seen in the paper.Also, the code contains scripts that include scripts and services to automatize the query execution.We use GraphDB (version 10.2.0) and Stardog (version 9.1.0) for the SPARQL endpoints. Because of the license restrictions, these software products cannot be included in this dataset and must be downloaded from the respective vendors. Also, the data must be loaded using the respective bulk loaders of GraphDB and Stardog.The datasets used in the experiments can be generated synthetic dataset generator of the WatDiv benchmark. The Wikidata dataset corresponds to the full RDF dump from May 22, 2023.Do not hesitate to contact the authors for any inquiries. }, affiliation = {Asma, Zubaria/FORT-ICS, Hernández, Daniel/University of Stuttgart, Galárraga, Luis/INRIA, Flouris, Giorgos/FORTH-ICS, Fundulaki, Irini/FORTH-ICS, Hose, Katja/TU Wien}, author = {Asma, Zubaria and Hernandez, Daniel and Galárraga, Luis and Flouris, Giorgos and Fundulaki, Irini and Hose, Katja}, doi = {10.18419/darus-3973}, howpublished = {Software}, note = {Related to: A. Zubaria, D. Hernández, L. Galárraga, G. Flouris, I. Fundulaki, and K. Hose. NPCS: Native Provenance Computation for SPARQL. Proceedings of the ACM Web Conference 2024 (WWW '24), May13-17, 2024, Singapore, Singapore, ACM, (May 2024). doi: 10.1145/3589334.3645557}, orcid-numbers = {Asma, Zubaria/0000-0002-9402-7487, Hernández, Daniel/0000-0002-7896-0875, Galárraga, Luis/0000-0002-0241-5379, Flouris, Giorgos/0000-0002-8937-4118, Fundulaki, Irini/0000-0002-4812-9896, Hose, Katja/0000-0001-7025-8099}, title = {Code and benchmark for NPCS, a Native Provenance Computation for SPARQL}, url = {https://doi.org/10.18419/darus-3973}, year = 2024 }
35. Asma, Z., Hernandez, D., Galárraga, L., Flouris, G., Fundulaki, I., & Hose, K. (2024). Code and benchmark for NPCS, a Native Provenance Computation for SPARQL. https://doi.org/10.18419/darus-3973
  - BibTeX
  BibTeX
  @misc{asma2024benchmark, abstract = {Code for the implementation and benchmark of NPCS, a Native Provenance Computation for SPARQL.The code in this dataset includes the implementation of the NPCS system, which is a middleware for SPARQL endpoints that rewrites queries to queries that annotate answers with provenance polynomials (i.e., how-provenance data). The translation rules implemented for the query rewriting can be seen in the paper.Also, the code contains scripts that include scripts and services to automatize the query execution.We use GraphDB (version 10.2.0) and Stardog (version 9.1.0) for the SPARQL endpoints. Because of the license restrictions, these software products cannot be included in this dataset and must be downloaded from the respective vendors. Also, the data must be loaded using the respective bulk loaders of GraphDB and Stardog.The datasets used in the experiments can be generated synthetic dataset generator of the WatDiv benchmark. The Wikidata dataset corresponds to the full RDF dump from May 22, 2023.Do not hesitate to contact the authors for any inquiries. }, affiliation = {Asma, Zubaria/FORT-ICS, Hernández, Daniel/University of Stuttgart, Galárraga, Luis/INRIA, Flouris, Giorgos/FORTH-ICS, Fundulaki, Irini/FORTH-ICS, Hose, Katja/TU Wien}, author = {Asma, Zubaria and Hernandez, Daniel and Galárraga, Luis and Flouris, Giorgos and Fundulaki, Irini and Hose, Katja}, doi = {10.18419/darus-3973}, howpublished = {Software}, note = {Related to: A. Zubaria, D. Hernández, L. Galárraga, G. Flouris, I. Fundulaki, and K. Hose. NPCS: Native Provenance Computation for SPARQL. Proceedings of the ACM Web Conference 2024 (WWW '24), May13-17, 2024, Singapore, Singapore, ACM, (May 2024). doi: 10.1145/3589334.3645557}, orcid-numbers = {Asma, Zubaria/0000-0002-9402-7487, Hernández, Daniel/0000-0002-7896-0875, Galárraga, Luis/0000-0002-0241-5379, Flouris, Giorgos/0000-0002-8937-4118, Fundulaki, Irini/0000-0002-4812-9896, Hose, Katja/0000-0001-7025-8099}, title = {Code and benchmark for NPCS, a Native Provenance Computation for SPARQL}, url = {https://doi.org/10.18419/darus-3973}, year = 2024 }
36. Chamon, L. F. O., Karimi, M. R., & Korba, A. (2024). Constrained Sampling with Primal-Dual Langevin Monte Carlo. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024). https://doi.org/10.48550/arXiv.2411.00568
  - BibTeX
  BibTeX
  @inproceedings{chamon2025constrainedsamplingprimalduallangevin, abstract = {This work considers the problem of sampling from a probability distribution known up to a normalization constant while satisfying a set of statistical constraints specified by the expected values of general nonlinear functions. This problem finds applications in, e.g., Bayesian inference, where it can constrain moments to evaluate counterfactual scenarios or enforce desiderata such as prediction fairness. Methods developed to handle support constraints, such as those based on mirror maps, barriers, and penalties, are not suited for this task. This work therefore relies on gradient descent-ascent dynamics in Wasserstein space to put forward a discrete-time primal-dual Langevin Monte Carlo algorithm (PD-LMC) that simultaneously constrains the target distribution and samples from it. We analyze the convergence of PD-LMC under standard assumptions on the target distribution and constraints, namely (strong) convexity and log-Sobolev inequalities. To do so, we bring classical optimization arguments for saddle-point algorithms to the geometry of Wasserstein space. We illustrate the relevance and effectiveness of PD-LMC in several applications.}, archiveprefix = {arXiv}, author = {Chamon, Luiz F. O. and Karimi, Mohammad Reza and Korba, Anna}, booktitle = {In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)}, doi = {https://doi.org/10.48550/arXiv.2411.00568}, eprint = {2411.00568}, eventtitle = {2024 Conference on Neural Information Processing Systems}, language = {en}, primaryclass = {stat.ML}, title = {Constrained Sampling with Primal-Dual Langevin Monte Carlo}, url = {https://arxiv.org/abs/2411.00568}, year = 2024 }
37. Chamon, L. F. O., Karimi, M. R., & Korba, A. (2024). Constrained Sampling with Primal-Dual Langevin Monte Carlo. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024). https://doi.org/10.48550/arXiv.2411.00568
  - BibTeX
  BibTeX
  @inproceedings{chamon2025constrainedsamplingprimalduallangevin, abstract = {This work considers the problem of sampling from a probability distribution known up to a normalization constant while satisfying a set of statistical constraints specified by the expected values of general nonlinear functions. This problem finds applications in, e.g., Bayesian inference, where it can constrain moments to evaluate counterfactual scenarios or enforce desiderata such as prediction fairness. Methods developed to handle support constraints, such as those based on mirror maps, barriers, and penalties, are not suited for this task. This work therefore relies on gradient descent-ascent dynamics in Wasserstein space to put forward a discrete-time primal-dual Langevin Monte Carlo algorithm (PD-LMC) that simultaneously constrains the target distribution and samples from it. We analyze the convergence of PD-LMC under standard assumptions on the target distribution and constraints, namely (strong) convexity and log-Sobolev inequalities. To do so, we bring classical optimization arguments for saddle-point algorithms to the geometry of Wasserstein space. We illustrate the relevance and effectiveness of PD-LMC in several applications.}, archiveprefix = {arXiv}, author = {Chamon, Luiz F. O. and Karimi, Mohammad Reza and Korba, Anna}, booktitle = {In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)}, doi = {https://doi.org/10.48550/arXiv.2411.00568}, eprint = {2411.00568}, eventtitle = {2024 Conference on Neural Information Processing Systems}, language = {en}, primaryclass = {stat.ML}, title = {Constrained Sampling with Primal-Dual Langevin Monte Carlo}, url = {https://arxiv.org/abs/2411.00568}, year = 2024 }
38. Crum, E., Santis, A. D., Ovide, M., Pan, J., Pisu, A., Lazzari, N., & Rudolph, S. (2024). Enriching Ontologies with Disjointness Axioms using Large Language Models. International Semantic Web Conference 2024. https://doi.org/10.48550/arXiv.2410.03235
  - BibTeX
  BibTeX
  @inproceedings{crum2024enrichingontologiesdisjointnessaxioms, archiveprefix = {arXiv}, author = {Crum, Elias and Santis, Antonio De and Ovide, Manon and Pan, Jiaxin and Pisu, Alessia and Lazzari, Nicolas and Rudolph, Sebastian}, booktitle = {Workshop on Knowledge Base Construction from Pre-Trained Language Models}, doi = {https://doi.org/10.48550/arXiv.2410.03235}, eprint = {2410.03235}, journal = {International Semantic Web Conference 2024}, language = {en}, primaryclass = {cs.AI}, title = {Enriching Ontologies with Disjointness Axioms using Large Language Models}, url = {https://arxiv.org/abs/2410.03235}, year = 2024 }
39. Crum, E., Santis, A. D., Ovide, M., Pan, J., Pisu, A., Lazzari, N., & Rudolph, S. (2024). Enriching Ontologies with Disjointness Axioms using Large Language Models. International Semantic Web Conference 2024. https://doi.org/10.48550/arXiv.2410.03235
  - BibTeX
  BibTeX
  @inproceedings{crum2024enrichingontologiesdisjointnessaxioms, archiveprefix = {arXiv}, author = {Crum, Elias and Santis, Antonio De and Ovide, Manon and Pan, Jiaxin and Pisu, Alessia and Lazzari, Nicolas and Rudolph, Sebastian}, booktitle = {Workshop on Knowledge Base Construction from Pre-Trained Language Models}, doi = {https://doi.org/10.48550/arXiv.2410.03235}, eprint = {2410.03235}, journal = {International Semantic Web Conference 2024}, language = {en}, primaryclass = {cs.AI}, title = {Enriching Ontologies with Disjointness Axioms using Large Language Models}, url = {https://arxiv.org/abs/2410.03235}, year = 2024 }
40. Das, A., Fathallah, N., & Obretincheva, N. (2024). Navigating Nulls, Numbers and Numerous Entities: Robust Knowledge Base Construction from Large Language Models. In Knowledge Base Construction from Pre-trained Language Models Challenge Workshop, ISWC′24.
  - BibTeX
  BibTeX
  @preprint{das2024navigating, author = {Das, Arunav and Fathallah, Nadeen and Obretincheva, Nicole}, booktitle = {Knowledge Base Construction from Pre-trained Language Models Challenge Workshop, ISWC'24.}, title = {Navigating Nulls, Numbers and Numerous Entities: Robust Knowledge Base Construction from Large Language Models.}, year = 2024 }
41. Das, A., Fathallah, N., & Obretincheva, N. (2024). Navigating Nulls, Numbers and Numerous Entities: Robust Knowledge Base Construction from Large Language Models. In Knowledge Base Construction from Pre-trained Language Models Challenge Workshop, ISWC′24.
  - BibTeX
  BibTeX
  @preprint{das2024navigating, author = {Das, Arunav and Fathallah, Nadeen and Obretincheva, Nicole}, booktitle = {Knowledge Base Construction from Pre-trained Language Models Challenge Workshop, ISWC'24.}, title = {Navigating Nulls, Numbers and Numerous Entities: Robust Knowledge Base Construction from Large Language Models.}, year = 2024 }
42. Diaz Ochoa, J. G., Mustafa, F. E., Weil, F., Wang, Y., Kama, K., & Knott, M. (2024). The aluminum standard: using generative Artificial Intelligence tools to synthesize and annotate non-structured patient data. BMC Medical Informatics and Decision Making, 24, Article 1. https://doi.org/10.1186/s12911-024-02825-4
  - BibTeX
  BibTeX
  @article{diazochoa2024aluminum, abstract = {Medical narratives are fundamental to the correct identification of a patient’s health condition. This is not only because it describes the patient’s situation. It also contains relevant information about the patient’s context and health state evolution. Narratives are usually vague and cannot be categorized easily. On the other hand, once the patient’s situation is correctly identified based on a narrative, it is then possible to map the patient’s situation into precise classification schemas and ontologies that are machine-readable. To this end, language models can be trained to read and extract elements from these narratives. However, the main problem is the lack of data for model identification and model training in languages other than English. First, gold standard annotations are usually not available due to the high level of data protection for patient data. Second, gold standard annotations (if available) are difficult to access. Alternative available data, like MIMIC (Sci Data 3:1, 2016) is written in English and for specific patient conditions like intensive care. Thus, when model training is required for other types of patients, like oncology (and not intensive care), this could lead to bias. To facilitate clinical narrative model training, a method for creating high-quality synthetic narratives is needed.}, author = {Diaz Ochoa, Juan G. and Mustafa, Faizan E. and Weil, Felix and Wang, Yi and Kama, Kudret and Knott, Markus}, doi = {10.1186/s12911-024-02825-4}, issn = {14726947}, journal = {BMC Medical Informatics and Decision Making}, number = 1, pages = {409--}, refid = {Diaz Ochoa2024}, title = {The aluminum standard: using generative Artificial Intelligence tools to synthesize and annotate non-structured patient data}, url = {https://doi.org/10.1186/s12911-024-02825-4}, volume = 24, year = 2024 }
43. Diaz Ochoa, J. G., Mustafa, F. E., Weil, F., Wang, Y., Kama, K., & Knott, M. (2024). The aluminum standard: using generative Artificial Intelligence tools to synthesize and annotate non-structured patient data. BMC Medical Informatics and Decision Making, 24, Article 1. https://doi.org/10.1186/s12911-024-02825-4
  - BibTeX
  BibTeX
  @article{diazochoa2024aluminum, abstract = {Medical narratives are fundamental to the correct identification of a patient’s health condition. This is not only because it describes the patient’s situation. It also contains relevant information about the patient’s context and health state evolution. Narratives are usually vague and cannot be categorized easily. On the other hand, once the patient’s situation is correctly identified based on a narrative, it is then possible to map the patient’s situation into precise classification schemas and ontologies that are machine-readable. To this end, language models can be trained to read and extract elements from these narratives. However, the main problem is the lack of data for model identification and model training in languages other than English. First, gold standard annotations are usually not available due to the high level of data protection for patient data. Second, gold standard annotations (if available) are difficult to access. Alternative available data, like MIMIC (Sci Data 3:1, 2016) is written in English and for specific patient conditions like intensive care. Thus, when model training is required for other types of patients, like oncology (and not intensive care), this could lead to bias. To facilitate clinical narrative model training, a method for creating high-quality synthetic narratives is needed.}, author = {Diaz Ochoa, Juan G. and Mustafa, Faizan E. and Weil, Felix and Wang, Yi and Kama, Kudret and Knott, Markus}, doi = {10.1186/s12911-024-02825-4}, issn = {14726947}, journal = {BMC Medical Informatics and Decision Making}, number = 1, pages = {409--}, refid = {Diaz Ochoa2024}, title = {The aluminum standard: using generative Artificial Intelligence tools to synthesize and annotate non-structured patient data}, url = {https://doi.org/10.1186/s12911-024-02825-4}, volume = 24, year = 2024 }

Publikationen

Unsere Publikationen

2025

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

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

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