%0 Conference Paper %1 he2024generatingsroiontologiesknowledge %A He, Yunjie %A Hernandez, Daniel %A Nayyeri, Mojtaba %A Xiong, Bo %A Zhu, Yuqicheng %A Kharlamov, Evgeny %A Staab, Steffen %B 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) %D 2024 %E Endriss, Ulle %E Melo, Francisco S. %E Bach, Kerstin %E Bugarín Diz, Alberto José %E Alonso-Moral, Jose Maria %E Barro, Senén %E Heintz, Fredrik %I IOS Press %K myown peer %P 4279 - 4286 %R 10.3233/FAIA241002 %T Generating SROI⁻ Ontologies via Knowledge Graph Query Embedding Learning %U https://doi.org/10.3233/FAIA241002 %V 392 %X 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. %@ 978-1-64368-548-9

@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.}, added-at = {2024-08-03T13:02:31.000+0200}, archiveprefix = {arXiv}, author = {He, Yunjie and Hernandez, Daniel and Nayyeri, Mojtaba and Xiong, Bo and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2ce63389bd3fdf763cc4d245ef89acd41/danielhz}, 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}, interhash = {6db9162559974867cb112e9e69d9b5a1}, intrahash = {ce63389bd3fdf763cc4d245ef89acd41}, isbn = {978-1-64368-548-9}, keywords = {myown peer}, language = {English}, month = oct, pages = {4279 - 4286}, preprinturl = {https://arxiv.org/abs/2407.09212}, primaryclass = {cs.AI}, publisher = {IOS Press}, series = {Frontiers in Artificial Intelligence and Applications}, timestamp = {2025-02-25T17:37:40.000+0100}, 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 }