Publikationen

2024

1. Asma, Z., Hernández, D., Galárraga, L., Flouris, G., Fundulaki, I., & Hose, K. (2024, Mai). NPCS: Native Provenance Computation for SPARQL. Proceedings of the ACM Web Conference 2024 (WWW ’24), May13--17, 2024, Singapore, Singapore. WWW ’24, 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 }
2. Asma, Z., Hernández, D., Galárraga, L., Flouris, G., Fundulaki, I., & Hose, K. (2024, Mai). NPCS: Native Provenance Computation for SPARQL. Proceedings of the ACM Web Conference 2024 (WWW ’24), May13--17, 2024, Singapore, Singapore. WWW ’24, 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 }
3. Blomqvist, E., García-Castro, R., Hernández, D., Hitzler, P., Lindecrantz, M., & Poveda-Villalón, M. (Hrsg.). (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) (Bd. 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 }
4. Blomqvist, E., García-Castro, R., Hernández, D., Hitzler, P., Lindecrantz, M., & Poveda-Villalón, M. (Hrsg.). (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) (Bd. 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 }
5. Elenter, J., Chamon, L. F. O., & Ribeiro, A. (2024, Mai). 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 }
6. Elenter, J., Chamon, L. F. O., & Ribeiro, A. (2024, Mai). 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 }
7. 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 }
8. 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 }
9. Errica, F., & Niepert, M. (2024, Mai). 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 }
10. Errica, F., & Niepert, M. (2024, Mai). 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 }
11. Hagnberger, J., Kalimuthu, M., Musekamp, D., & Niepert, M. (2024, Mai). 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 }
12. Hagnberger, J., Kalimuthu, M., Musekamp, D., & Niepert, M. (2024, Mai). 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 }
13. Liu, A., Niepert, M., & den Broeck, G. V. (2024, Mai). 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 }
14. Liu, A., Niepert, M., & den Broeck, G. V. (2024, Mai). 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 }
15. Qian, C., Manolache, A., Ahmed, K., Zeng, Z., den Broeck, G. V., Niepert, M., & Morris, C. (2024, Mai). 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 }
16. Qian, C., Manolache, A., Ahmed, K., Zeng, Z., den Broeck, G. V., Niepert, M., & Morris, C. (2024, Mai). 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 }
17. Seifer, P., Hernández, D., Lämmel, R., & Staab, S. (2024, Mai). 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. WWW ’24, 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 }
18. Seifer, P., Hernández, D., Lämmel, R., & Staab, S. (2024, Mai). 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. WWW ’24, 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 }
19. Tran, H.-C., Nguyen, D. M. H., Nguyen, M.-D., Le, N. H., & T. Nguyen, B. (2024, Mai). 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 }
20. Tran, H.-C., Nguyen, D. M. H., Nguyen, M.-D., Le, N. H., & T. Nguyen, B. (2024, Mai). 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 }
21. Zubaria, A., Hernández, D., Galárraga, L., Flouris, G., Fundulaki, I., & Hose, K. (2024, Mai). NPCS: Native Provenance Computation for SPARQL. Proceedings of the ACM Web Conference 2024 (WWW ’24), May13--17, 2024, Singapore, Singapore. WWW ’24, 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 }
22. Zubaria, A., Hernández, D., Galárraga, L., Flouris, G., Fundulaki, I., & Hose, K. (2024, Mai). NPCS: Native Provenance Computation for SPARQL. Proceedings of the ACM Web Conference 2024 (WWW ’24), May13--17, 2024, Singapore, Singapore. WWW ’24, 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 }
23. Zubaria, A., Hernández, D., Galárraga, L., Flouris, G., Fundulaki, I., & Hose, K. (2024, Mai). NPCS: Native Provenance Computation for SPARQL. Proceedings of the ACM Web Conference 2024 (WWW ’24), May13--17, 2024, Singapore, Singapore. WWW ’24, 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 }
24. 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 }
25. 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 }
26. Ding, Z., Cai, H., Wu, J., Ma, Y., Liao, R., Xiong, B., & Tresp, V. (2024). zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models. Annual Conference of the North American Chapter of the Association for Computational Linguistics. https://arxiv.org/abs/2311.10112
    • BibTeX

    BibTeX

    @article{ding2023zeroshot, abbr = {NAACL}, arxiv = {2311.10112}, author = {Ding, Zifeng and Cai, Heling and Wu, Jingpei and Ma, Yunpu and Liao, Ruotong and Xiong, Bo and Tresp, Volker}, journal = {Annual Conference of the North American Chapter of the Association for Computational Linguistics}, title = {zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models}, url = {https://arxiv.org/abs/2311.10112}, year = 2024 }
27. Hagnberger, J., Kalimuthu, M., Musekamp, D., & Niepert, M. (2024). Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations. In Proceedings of the 41st International Conference on Machine Learning (ICML 2024). https://arxiv.org/abs/2406.03919
    • BibTeX

    BibTeX

    @inproceedings{hagnberger2024vectorizedconditionalneuralfields, abstract = {Transformer models are increasingly used for solving Partial Differential Equations (PDEs). Several adaptations have been proposed, all of which suffer from the typical problems of Transformers, such as quadratic memory and time complexity. Furthermore, all prevalent architectures for PDE solving lack at least one of several desirable properties of an ideal surrogate model, such as (i) generalization to PDE parameters not seen during training, (ii) spatial and temporal zero-shot super-resolution, (iii) continuous temporal extrapolation, (iv) support for 1D, 2D, and 3D PDEs, and (v) efficient inference for longer temporal rollouts. To address these limitations, we propose Vectorized Conditional Neural Fields (VCNeFs), which represent the solution of time-dependent PDEs as neural fields. Contrary to prior methods, however, VCNeFs compute, for a set of multiple spatio-temporal query points, their solutions in parallel and model their dependencies through attention mechanisms. Moreover, VCNeF can condition the neural field on both the initial conditions and the parameters of the PDEs. An extensive set of experiments demonstrates that VCNeFs are competitive with and often outperform existing ML-based surrogate models.}, archiveprefix = {arXiv}, author = {Hagnberger, Jan and Kalimuthu, Marimuthu and Musekamp, Daniel and Niepert, Mathias}, booktitle = {In Proceedings of the 41st International Conference on Machine Learning (ICML 2024)}, eprint = {2406.03919}, language = {en}, primaryclass = {cs.LG}, title = {Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations}, url = {https://arxiv.org/abs/2406.03919}, year = 2024 }
28. Hagnberger, J., Kalimuthu, M., Musekamp, D., & Niepert, M. (2024). Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations. In Proceedings of the 41st International Conference on Machine Learning (ICML 2024). https://arxiv.org/abs/2406.03919
    • BibTeX

    BibTeX

    @inproceedings{hagnberger2024vectorizedconditionalneuralfields, abstract = {Transformer models are increasingly used for solving Partial Differential Equations (PDEs). Several adaptations have been proposed, all of which suffer from the typical problems of Transformers, such as quadratic memory and time complexity. Furthermore, all prevalent architectures for PDE solving lack at least one of several desirable properties of an ideal surrogate model, such as (i) generalization to PDE parameters not seen during training, (ii) spatial and temporal zero-shot super-resolution, (iii) continuous temporal extrapolation, (iv) support for 1D, 2D, and 3D PDEs, and (v) efficient inference for longer temporal rollouts. To address these limitations, we propose Vectorized Conditional Neural Fields (VCNeFs), which represent the solution of time-dependent PDEs as neural fields. Contrary to prior methods, however, VCNeFs compute, for a set of multiple spatio-temporal query points, their solutions in parallel and model their dependencies through attention mechanisms. Moreover, VCNeF can condition the neural field on both the initial conditions and the parameters of the PDEs. An extensive set of experiments demonstrates that VCNeFs are competitive with and often outperform existing ML-based surrogate models.}, archiveprefix = {arXiv}, author = {Hagnberger, Jan and Kalimuthu, Marimuthu and Musekamp, Daniel and Niepert, Mathias}, booktitle = {In Proceedings of the 41st International Conference on Machine Learning (ICML 2024)}, eprint = {2406.03919}, language = {en}, primaryclass = {cs.LG}, title = {Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations}, url = {https://arxiv.org/abs/2406.03919}, year = 2024 }
29. He, Y., Hernandez, D., Nayyeri, M., Xiong, B., Zhu, Y., Kharlamov, E., & Staab, S. (2024). Generating SROI^- Ontologies via Knowledge Graph Query Embedding Learning. https://arxiv.org/abs/2407.09212
    • BibTeX

    BibTeX

    @preprint{he2024generatingsroiontologiesknowledge, archiveprefix = {arXiv}, author = {He, Yunjie and Hernandez, Daniel and Nayyeri, Mojtaba and Xiong, Bo and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, eprint = {2407.09212}, primaryclass = {cs.AI}, title = {Generating SROI^{-} Ontologies via Knowledge Graph Query Embedding Learning}, url = {https://arxiv.org/abs/2407.09212}, year = 2024 }
30. He, Y., Hernandez, D., Nayyeri, M., Xiong, B., Zhu, Y., Kharlamov, E., & Staab, S. (2024). Generating SROI^- Ontologies via Knowledge Graph Query Embedding Learning. https://arxiv.org/abs/2407.09212
    • BibTeX

    BibTeX

    @preprint{he2024generatingsroiontologiesknowledge, archiveprefix = {arXiv}, author = {He, Yunjie and Hernandez, Daniel and Nayyeri, Mojtaba and Xiong, Bo and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, eprint = {2407.09212}, primaryclass = {cs.AI}, title = {Generating SROI^{-} Ontologies via Knowledge Graph Query Embedding Learning}, url = {https://arxiv.org/abs/2407.09212}, year = 2024 }
31. He, Y., Hernandez, D., Nayyeri, M., Xiong, B., Zhu, Y., Kharlamov, E., & Staab, S. (2024). Generating SROI^- Ontologies via Knowledge Graph Query Embedding Learning. https://arxiv.org/abs/2407.09212
    • BibTeX

    BibTeX

    @preprint{he2024generatingsroiontologiesknowledge, archiveprefix = {arXiv}, author = {He, Yunjie and Hernandez, Daniel and Nayyeri, Mojtaba and Xiong, Bo and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, eprint = {2407.09212}, primaryclass = {cs.AI}, title = {Generating SROI^{-} Ontologies via Knowledge Graph Query Embedding Learning}, url = {https://arxiv.org/abs/2407.09212}, year = 2024 }
32. Nguyen, D. M. H., Le, A. T., Nguyen, T. Q., Diep, N. T., Nguyen, T., Duong-Tran, D., Peters, J., Shen, L., Niepert, M., & Sonntag, D. (2024). Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model. Proceedings of Machine Learning Research. https://arxiv.org/abs/2407.04489
    • BibTeX

    BibTeX

    @inproceedings{nguyen2024dudedualdistributionawarecontext, abstract = {Prompt learning methods are gaining increasing attention due to their ability to customize large vision-language models to new domains using pre-trained contextual knowledge and minimal training data. However, existing works typically rely on optimizing unified prompt inputs, often struggling with fine-grained classification tasks due to insufficient discriminative attributes. To tackle this, we consider a new framework based on a dual context of both domain-shared and class-specific contexts, where the latter is generated by Large Language Models (LLMs) such as GPTs. Such dual prompt methods enhance the model's feature representation by joining implicit and explicit factors encoded in LLM knowledge. Moreover, we formulate the Unbalanced Optimal Transport (UOT) theory to quantify the relationships between constructed prompts and visual tokens. Through partial matching, UOT can properly align discrete sets of visual tokens and prompt embeddings under different mass distributions, which is particularly valuable for handling irrelevant or noisy elements, ensuring that the preservation of mass does not restrict transport solutions. Furthermore, UOT's characteristics integrate seamlessly with image augmentation, expanding the training sample pool while maintaining a reasonable distance between perturbed images and prompt inputs. Extensive experiments across few-shot classification and adapter settings substantiate the superiority of our model over current state-of-the-art baselines.}, archiveprefix = {arXiv}, author = {Nguyen, Duy M. H. and Le, An T. and Nguyen, Trung Q. and Diep, Nghiem T. and Nguyen, Tai and Duong-Tran, Duy and Peters, Jan and Shen, Li and Niepert, Mathias and Sonntag, Daniel}, booktitle = {Proceedings of Machine Learning Research}, eprint = {2407.04489}, language = {en}, primaryclass = {cs.CV}, title = {Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model}, url = {https://arxiv.org/abs/2407.04489}, venue = {Asian Conference on Machine Learning, ACML 2024}, year = 2024 }
33. Nguyen, D. M. H., Le, A. T., Nguyen, T. Q., Diep, N. T., Nguyen, T., Duong-Tran, D., Peters, J., Shen, L., Niepert, M., & Sonntag, D. (2024). Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model. Proceedings of Machine Learning Research. https://arxiv.org/abs/2407.04489
    • BibTeX

    BibTeX

    @inproceedings{nguyen2024dudedualdistributionawarecontext, abstract = {Prompt learning methods are gaining increasing attention due to their ability to customize large vision-language models to new domains using pre-trained contextual knowledge and minimal training data. However, existing works typically rely on optimizing unified prompt inputs, often struggling with fine-grained classification tasks due to insufficient discriminative attributes. To tackle this, we consider a new framework based on a dual context of both domain-shared and class-specific contexts, where the latter is generated by Large Language Models (LLMs) such as GPTs. Such dual prompt methods enhance the model's feature representation by joining implicit and explicit factors encoded in LLM knowledge. Moreover, we formulate the Unbalanced Optimal Transport (UOT) theory to quantify the relationships between constructed prompts and visual tokens. Through partial matching, UOT can properly align discrete sets of visual tokens and prompt embeddings under different mass distributions, which is particularly valuable for handling irrelevant or noisy elements, ensuring that the preservation of mass does not restrict transport solutions. Furthermore, UOT's characteristics integrate seamlessly with image augmentation, expanding the training sample pool while maintaining a reasonable distance between perturbed images and prompt inputs. Extensive experiments across few-shot classification and adapter settings substantiate the superiority of our model over current state-of-the-art baselines.}, archiveprefix = {arXiv}, author = {Nguyen, Duy M. H. and Le, An T. and Nguyen, Trung Q. and Diep, Nghiem T. and Nguyen, Tai and Duong-Tran, Duy and Peters, Jan and Shen, Li and Niepert, Mathias and Sonntag, Daniel}, booktitle = {Proceedings of Machine Learning Research}, eprint = {2407.04489}, language = {en}, primaryclass = {cs.CV}, title = {Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model}, url = {https://arxiv.org/abs/2407.04489}, venue = {Asian Conference on Machine Learning, ACML 2024}, year = 2024 }
34. Nguyen, D. M. H., Lukashina, N., Nguyen, T., Le, A. T., Nguyen, T., Ho, N., Peters, J., Sonntag, D., Zaverkin, V., & Niepert, M. (2024). Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks. In Proceedings of the 41st International Conference on Machine Learning (ICML 2024). https://arxiv.org/abs/2402.01975
    • BibTeX

    BibTeX

    @inproceedings{nguyen2024structureawaree3invariantmolecularconformer, abstract = {A molecule's 2D representation consists of its atoms, their attributes, and the molecule's covalent bonds. A 3D (geometric) representation of a molecule is called a conformer and consists of its atom types and Cartesian coordinates. Every conformer has a potential energy, and the lower this energy, the more likely it occurs in nature. Most existing machine learning methods for molecular property prediction consider either 2D molecular graphs or 3D conformer structure representations in isolation. Inspired by recent work on using ensembles of conformers in conjunction with 2D graph representations, we propose E(3)-invariant molecular conformer aggregation networks. The method integrates a molecule's 2D representation with that of multiple of its conformers. Contrary to prior work, we propose a novel 2D-3D aggregation mechanism based on a differentiable solver for the Fused Gromov-Wasserstein Barycenter problem and the use of an efficient conformer generation method based on distance geometry. We show that the proposed aggregation mechanism is E(3) invariant and propose an efficient GPU implementation. Moreover, we demonstrate that the aggregation mechanism helps to significantly outperform state-of-the-art molecule property prediction methods on established datasets.}, archiveprefix = {arXiv}, author = {Nguyen, Duy M. H. and Lukashina, Nina and Nguyen, Tai and Le, An T. and Nguyen, TrungTin and Ho, Nhat and Peters, Jan and Sonntag, Daniel and Zaverkin, Viktor and Niepert, Mathias}, booktitle = {In Proceedings of the 41st International Conference on Machine Learning (ICML 2024)}, eprint = {2402.01975}, language = {en}, primaryclass = {cs.LG}, title = {Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks}, url = {https://arxiv.org/abs/2402.01975}, year = 2024 }
35. Nguyen, D. M. H., Lukashina, N., Nguyen, T., Le, A. T., Nguyen, T., Ho, N., Peters, J., Sonntag, D., Zaverkin, V., & Niepert, M. (2024). Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks. In Proceedings of the 41st International Conference on Machine Learning (ICML 2024). https://arxiv.org/abs/2402.01975
    • BibTeX

    BibTeX

    @inproceedings{nguyen2024structureawaree3invariantmolecularconformer, abstract = {A molecule's 2D representation consists of its atoms, their attributes, and the molecule's covalent bonds. A 3D (geometric) representation of a molecule is called a conformer and consists of its atom types and Cartesian coordinates. Every conformer has a potential energy, and the lower this energy, the more likely it occurs in nature. Most existing machine learning methods for molecular property prediction consider either 2D molecular graphs or 3D conformer structure representations in isolation. Inspired by recent work on using ensembles of conformers in conjunction with 2D graph representations, we propose E(3)-invariant molecular conformer aggregation networks. The method integrates a molecule's 2D representation with that of multiple of its conformers. Contrary to prior work, we propose a novel 2D-3D aggregation mechanism based on a differentiable solver for the Fused Gromov-Wasserstein Barycenter problem and the use of an efficient conformer generation method based on distance geometry. We show that the proposed aggregation mechanism is E(3) invariant and propose an efficient GPU implementation. Moreover, we demonstrate that the aggregation mechanism helps to significantly outperform state-of-the-art molecule property prediction methods on established datasets.}, archiveprefix = {arXiv}, author = {Nguyen, Duy M. H. and Lukashina, Nina and Nguyen, Tai and Le, An T. and Nguyen, TrungTin and Ho, Nhat and Peters, Jan and Sonntag, Daniel and Zaverkin, Viktor and Niepert, Mathias}, booktitle = {In Proceedings of the 41st International Conference on Machine Learning (ICML 2024)}, eprint = {2402.01975}, language = {en}, primaryclass = {cs.LG}, title = {Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks}, url = {https://arxiv.org/abs/2402.01975}, year = 2024 }
36. Pan, J., Nayyeri, M., Li, Y., & Staab, S. (2024). HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces. Thirty-eighth Conference on Artificial Intelligence, AAAI, 2024, Vancouver, Canada, February 22 – February 25, 2024,.
    • BibTeX

    BibTeX

    @inproceedings{pan2023hge, abstract = {Temporal knowledge graphs represent temporal facts (s,p,o,τ) relating a subject s and an object o via a relation label p at time τ, where τ could be a time point or time interval. Temporal knowledge graphs may exhibit static temporal patterns at distinct points in time and dynamic temporal patterns between different timestamps. In order to learn a rich set of static and dynamic temporal patterns and apply them for inference, several embedding approaches have been suggested in the literature. However, as most of them resort to single underlying embedding spaces, their capability to model all kinds of temporal patterns was severely limited by having to adhere to the geometric property of their one embedding space. We lift this limitation by an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties, i.e.\ Complex, Dual, and Split-complex spaces. In addition, we propose a temporal-geometric attention mechanism to integrate information from different geometric subspaces conveniently according to the captured relational and temporal information. Experimental results on standard temporal benchmark datasets favorably evaluate our approach against state-of-the-art models.}, author = {Pan, Jiaxin and Nayyeri, Mojtaba and Li, Yinan and Staab, Steffen}, booktitle = {Thirty-eighth Conference on Artificial Intelligence, {AAAI}, 2024, Vancouver, Canada, February 22 – February 25, 2024,}, eventdate = {22 February 2024 – 25 February 2024}, preprinturl = {https://arxiv.org/abs/2312.13680}, title = {HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces}, year = 2024 }
37. Pan, J., Nayyeri, M., Li, Y., & Staab, S. (2024). HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces. Thirty-eighth Conference on Artificial Intelligence, AAAI, 2024, Vancouver, Canada, February 22 – February 25, 2024,.
    • BibTeX

    BibTeX

    @inproceedings{pan2023hge, abstract = {Temporal knowledge graphs represent temporal facts (s,p,o,τ) relating a subject s and an object o via a relation label p at time τ, where τ could be a time point or time interval. Temporal knowledge graphs may exhibit static temporal patterns at distinct points in time and dynamic temporal patterns between different timestamps. In order to learn a rich set of static and dynamic temporal patterns and apply them for inference, several embedding approaches have been suggested in the literature. However, as most of them resort to single underlying embedding spaces, their capability to model all kinds of temporal patterns was severely limited by having to adhere to the geometric property of their one embedding space. We lift this limitation by an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties, i.e.\ Complex, Dual, and Split-complex spaces. In addition, we propose a temporal-geometric attention mechanism to integrate information from different geometric subspaces conveniently according to the captured relational and temporal information. Experimental results on standard temporal benchmark datasets favorably evaluate our approach against state-of-the-art models.}, author = {Pan, Jiaxin and Nayyeri, Mojtaba and Li, Yinan and Staab, Steffen}, booktitle = {Thirty-eighth Conference on Artificial Intelligence, {AAAI}, 2024, Vancouver, Canada, February 22 – February 25, 2024,}, eventdate = {22 February 2024 – 25 February 2024}, preprinturl = {https://arxiv.org/abs/2312.13680}, title = {HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces}, year = 2024 }
38. Pan, X., Hernández, D., Seifer, P., Lämmel, R., & Staab, S. (2024). eSPARQL: Representing and Reconciling Agnostic and Atheistic Beliefs in RDF-star Knowledge Graphs. https://arxiv.org/abs/2407.21483
    • BibTeX

    BibTeX

    @preprint{pan2024esparqlrepresentingreconcilingagnostic, archiveprefix = {arXiv}, author = {Pan, Xiny and Hernández, Daniel and Seifer, Philipp and Lämmel, Ralf and Staab, Steffen}, eprint = {2407.21483}, primaryclass = {cs.AI}, title = {eSPARQL: Representing and Reconciling Agnostic and Atheistic Beliefs in RDF-star Knowledge Graphs}, url = {https://arxiv.org/abs/2407.21483}, year = 2024 }
39. Pan, X., Hernández, D., Seifer, P., Lämmel, R., & Staab, S. (2024). eSPARQL: Representing and Reconciling Agnostic and Atheistic Beliefs in RDF-star Knowledge Graphs. https://arxiv.org/abs/2407.21483
    • BibTeX

    BibTeX

    @preprint{pan2024esparqlrepresentingreconcilingagnostic, archiveprefix = {arXiv}, author = {Pan, Xiny and Hernández, Daniel and Seifer, Philipp and Lämmel, Ralf and Staab, Steffen}, eprint = {2407.21483}, primaryclass = {cs.AI}, title = {eSPARQL: Representing and Reconciling Agnostic and Atheistic Beliefs in RDF-star Knowledge Graphs}, url = {https://arxiv.org/abs/2407.21483}, year = 2024 }
40. Pan, X., Hernández, D., Seifer, P., Lämmel, R., & Staab, S. (2024). eSPARQL: Representing and Reconciling Agnostic and Atheistic Beliefs in RDF-star Knowledge Graphs. https://arxiv.org/abs/2407.21483
    • BibTeX

    BibTeX

    @preprint{pan2024esparqlrepresentingreconcilingagnostic, archiveprefix = {arXiv}, author = {Pan, Xinyi and Hernández, Daniel and Seifer, Philipp and Lämmel, Ralf and Staab, Steffen}, eprint = {2407.21483}, primaryclass = {cs.AI}, title = {eSPARQL: Representing and Reconciling Agnostic and Atheistic Beliefs in RDF-star Knowledge Graphs}, url = {https://arxiv.org/abs/2407.21483}, year = 2024 }
41. Peng, K., Yin, C., Zheng, J., Liu, R., Schneider, D., Zhang, J., Yang, K., Sarfraz, M. S., Stiefelhagen, R., & Roitberg, A. (2024). Navigating Open Set Scenarios for Skeleton-based Action Recognition. The 38th Annual AAAI Conference on Artificial Intelligence. https://arxiv.org/abs/2312.06330
    • BibTeX

    BibTeX

    @article{peng2023navigating, author = {Peng, Kunyu and Yin, Cheng and Zheng, Junwei and Liu, Ruiping and Schneider, David and Zhang, Jiaming and Yang, Kailun and Sarfraz, M Saquib and Stiefelhagen, Rainer and Roitberg, Alina}, booktitle = {The 38th Annual AAAI Conference on Artificial Intelligence}, title = {Navigating Open Set Scenarios for Skeleton-based Action Recognition}, url = {https://arxiv.org/abs/2312.06330}, year = 2024 }
42. Peng, K., Yin, C., Zheng, J., Liu, R., Schneider, D., Zhang, J., Yang, K., Sarfraz, M. S., Stiefelhagen, R., & Roitberg, A. (2024). Navigating Open Set Scenarios for Skeleton-based Action Recognition. The 38th Annual AAAI Conference on Artificial Intelligence. https://arxiv.org/abs/2312.06330
    • BibTeX

    BibTeX

    @article{peng2023navigating, author = {Peng, Kunyu and Yin, Cheng and Zheng, Junwei and Liu, Ruiping and Schneider, David and Zhang, Jiaming and Yang, Kailun and Sarfraz, M Saquib and Stiefelhagen, Rainer and Roitberg, Alina}, booktitle = {The 38th Annual AAAI Conference on Artificial Intelligence}, title = {Navigating Open Set Scenarios for Skeleton-based Action Recognition}, url = {https://arxiv.org/abs/2312.06330}, year = 2024 }
43. Potyka, N., Zhu, Y., He, Y., Kharlamov, E., & Staab, S. (2024). Robust Knowledge Extraction from Large Language Models using Social Choice Theory. In Proceedings of the 23rd International Conference on Autonomous Agents and Multi-Agent Systems. https://arxiv.org/abs/2312.14877
    • BibTeX

    BibTeX

    @inproceedings{noauthororeditor2023robust, abstract = {Large-language models (LLMs) have the potential to support a wide range of applications like conversational agents, creative writing, text improvement, and general query answering. However, they are ill-suited for query answering in high-stake domains like medicine because they generate answers at random and their answers are typically not robust - even the same query can result in different answers when prompted multiple times. In order to improve the robustness of LLM queries, we propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory. We study ranking queries in diagnostic settings like medical and fault diagnosis and discuss how the Partial Borda Choice function from the literature can be applied to merge multiple query results. We discuss some additional interesting properties in our setting and evaluate the robustness of our approach empirically.}, author = {Potyka, Nico and Zhu, Yuqicheng and He, Yunjie and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {In Proceedings of the 23rd International Conference on Autonomous Agents and Multi-Agent Systems}, title = {Robust Knowledge Extraction from Large Language Models using Social Choice Theory}, url = {https://arxiv.org/abs/2312.14877}, year = 2024 }
44. Potyka, N., Zhu, Y., He, Y., Kharlamov, E., & Staab, S. (2024). Robust Knowledge Extraction from Large Language Models using Social Choice Theory. In Proceedings of the 23rd International Conference on Autonomous Agents and Multi-Agent Systems. https://arxiv.org/abs/2312.14877
    • BibTeX

    BibTeX

    @inproceedings{potyka2024robust, abstract = {Large-language models (LLMs) have the potential to support a wide range of applications like conversational agents, creative writing, text improvement, and general query answering. However, they are ill-suited for query answering in high-stake domains like medicine because they generate answers at random and their answers are typically not robust - even the same query can result in different answers when prompted multiple times. In order to improve the robustness of LLM queries, we propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory. We study ranking queries in diagnostic settings like medical and fault diagnosis and discuss how the Partial Borda Choice function from the literature can be applied to merge multiple query results. We discuss some additional interesting properties in our setting and evaluate the robustness of our approach empirically.}, author = {Potyka, Nico and Zhu, Yuqicheng and He, Yunjie and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {In Proceedings of the 23rd International Conference on Autonomous Agents and Multi-Agent Systems}, title = {Robust Knowledge Extraction from Large Language Models using Social Choice Theory}, url = {https://arxiv.org/abs/2312.14877}, year = 2024 }
45. Potyka, N., Zhu, Y., He, Y., Kharlamov, E., & Staab, S. (2024). Robust Knowledge Extraction from Large Language Models using Social Choice Theory. The 23rd International Conference on Autonomous Agents and Multi-Agent Systems. https://arxiv.org/abs/2312.14877
    • BibTeX

    BibTeX

    @conference{noauthororeditor2023robust, abstract = {Large-language models (LLMs) have the potential to support a wide range of applications like conversational agents, creative writing, text improvement, and general query answering. However, they are ill-suited for query answering in high-stake domains like medicine because they generate answers at random and their answers are typically not robust - even the same query can result in different answers when prompted multiple times. In order to improve the robustness of LLM queries, we propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory. We study ranking queries in diagnostic settings like medical and fault diagnosis and discuss how the Partial Borda Choice function from the literature can be applied to merge multiple query results. We discuss some additional interesting properties in our setting and evaluate the robustness of our approach empirically.}, author = {Potyka, Nico and Zhu, Yuqicheng and He, Yunjie and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {The 23rd International Conference on Autonomous Agents and Multi-Agent Systems}, title = {Robust Knowledge Extraction from Large Language Models using Social Choice Theory}, url = {https://arxiv.org/abs/2312.14877}, year = 2024 }
46. Schwindt, S., Meisinger, L., Negreiros, B., Schneider, T., & Nowak, W. (2024). Transfer learning achieves high recall for object classification in fluvial environments with limited data. Geomorphology, 455, 109185. https://doi.org/10.1016/j.geomorph.2024.109185
    • BibTeX

    BibTeX

    @inproceedings{SCHWINDT2024109185, abstract = {Field surveys to collect data from fluvial ecosystems traditionally focus on specific phenomena related to geomorphology or hydrology. Low-cost unmanned aerial vehicles (UAVs) additionally empower the fast and massive collection of airborne photogrammetry, providing geospatially explicit information. This remote sensing data complements field surveys by offering contextual information on geomorphological conditions, including digital terrain models. AI-based image recognition can augment contextual information to extrapolate archetypal object classes through name labels, such as “gravel”, “sand”, “plant”, or “large wood”. However, obtaining sufficient ground truth data for these classifications, particularly in morphodynamic fluvial environments, is challenging and induces high costs. This study introduces a transfer learning approach to address the challenge of low data availability, enabling AI-based mapping of complex objects in fluvial landscapes. We leverage the learned general structure of a deep convolutional neural network (CNN) pre-trained on a broad range of images. The fixed latent features of the pre-trained CNN stem from GoogLeNet. A fixed feature extractor serves to classify objects with limited data amounts. Satisfactory performance is measured with a recall rate, expressing the ability of a model to find all occurrences of a class on an image. High spatial heterogeneity in the locations of measurements on the x-y plane improves model performance. With a minimum of 400 labeled instances, the model achieves a satisfactory 93.75-% recall for a “large wood” target class, providing evidence of the effectiveness of transfer learning in remote sensing for geomorphological studies. This ability to detect large woods in river environments is critical to restoration efforts as it helps create fish habitat, which is essential to supporting biodiversity.}, author = {Schwindt, Sebastian and Meisinger, Lisa and Negreiros, Beatriz and Schneider, Tim and Nowak, Wolfgang}, doi = {https://doi.org/10.1016/j.geomorph.2024.109185}, issn = {0169-555X}, journal = {Geomorphology}, language = {en}, pages = 109185, title = {Transfer learning achieves high recall for object classification in fluvial environments with limited data}, url = {https://www.sciencedirect.com/science/article/pii/S0169555X24001351}, volume = 455, year = 2024 }
47. Seifer, P., Hernández, D., Lämmel, R., & Staab, S. (2024). From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries. Proceedings of the ACM Web Conference 2024, WWW 2024, Singapore, 13 - 17 May 2024.
    • 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} 2024, Singapore, 13 - 17 May 2024}, eventdate = {13 May 2024 - 17 May 2024}, publisher = {ACM}, title = {From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries}, venue = {Singapore}, year = 2024 }
48. Seifer, P., Hernández, D., Lämmel, R., & Staab, S. (2024). From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries. WWW ’24: The ACM Web Conference 2024 Proceedings. WWW ’24, 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 = {WWW '24: The ACM Web Conference 2024 Proceedings}, doi = {10.1145/3589334.3645550}, eventdate = {May 13–17, 2024}, eventtitle = {WWW '24}, isbn = {979-8-4007-0171-9/24/05}, publisher = {ACM}, title = {From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries}, venue = {Singapore}, year = 2024 }
49. Seifer, P., Hernández, D., Lämmel, R., & Staab, S. (2024). Code for From Shapes to Shapes. https://doi.org/10.18419/darus-3977
    • BibTeX

    BibTeX

    @misc{seifer2024shapes, abstract = {This dataset contains the implementation code for an algorithm to infer SHACL shapes that the graph returned by an SPARQL CONSTRUCT query must satisfy if the input satisfies a given set of SHACL shapes. This dataset also includes an evaluation for the algorithm. The algorithm implemented in this dataset is proposed in the paper From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries. To execute the code, follow the instructions in the README.md file. For more info, please check the paper, and please have no hesitation to contact the authors for any inquiries. }, affiliation = {Seifer, Philipp/University of Koblenz, Hernández, Daniel/University of Stuttgart, Lämmel, Ralf/University of Koblenz, Staab, Steffen/University of Stuttgart}, author = {Seifer, Philipp and Hernández, Daniel and Lämmel, Ralf and Staab, Steffen}, doi = {10.18419/darus-3977}, howpublished = {Software}, note = {Related to: Philipp Seifer, Daniel Hernández, Ralf Lämmel, and Steffen Staab. 2024. From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries. In Proceedings of the ACM Web Conference 2024 (WWW ’24). ACM. doi: 10.1145/3589334.3645550}, orcid-numbers = {Seifer, Philipp/0000-0002-7421-2060, Hernández, Daniel/0000-0002-7896-0875, Lämmel, Ralf/0000-0001-9946-4363, Staab, Steffen/0000-0002-0780-4154}, title = {Code for From Shapes to Shapes}, year = 2024 }
50. Serra, G., & Niepert, M. (2024). L2XGNN: Learning to Explain Graph Neural Networks. Machine Learning Journal. https://arxiv.org/abs/2209.14402
    • BibTeX

    BibTeX

    @inproceedings{serra2024l2xgnnlearningexplaingraph, abstract = {Graph Neural Networks (GNNs) are a popular class of machine learning models. Inspired by the learning to explain (L2X) paradigm, we propose L2XGNN, a framework for explainable GNNs that provides faithful explanations by design. L2XGNN learns a mechanism for selecting explanatory subgraphs (motifs), which are exclusively used in the GNN message-passing operations. L2XGNN can select, for each input graph, a subgraph with specific properties, such as being sparse and connected. Imposing such constraints on the motifs often leads to more interpretable and effective explanations. Experiments on several datasets suggest that L2XGNN achieves the same classification accuracy as baseline methods using the entire input graph while ensuring that only the provided explanations are used to make predictions. Moreover, we show that L2XGNN can identify motifs responsible for the graph's properties it is intended to predict.}, archiveprefix = {arXiv}, author = {Serra, Giuseppe and Niepert, Mathias}, booktitle = {Proceedings of the European Conference on Machine Learning(ECML 2024)}, eprint = {2209.14402}, journal = {Machine Learning Journal}, language = {en}, primaryclass = {cs.LG}, title = {L2XGNN: Learning to Explain Graph Neural Networks}, url = {https://arxiv.org/abs/2209.14402}, year = 2024 }