ABSTRACT
Knowledge graphs (KGs) naturally capture the convergence of data and knowledge, making them expressive frameworks for describing and integrating heterogeneous data in a coherent and interconnected manner. However, based on the Open World Assumption (OWA), the absence of information within KGs does not indicate falsity or non-existence; it merely reflects incompleteness. Inductive learning over KGs involves predicting new relationships based on existing statements in the KG, using either numerical or symbolic learning models. The Partial Completeness Assumption (PCA) heuristic efficiently guides inductive learning methods for Link Prediction (LP) by refining predictions about absent KG relationships. Nevertheless, numeric techniques– like KG embedding models– alone may fall short in accurately predicting missing information, particularly when it comes to capturing implicit knowledge and complex relationships. We propose a hybrid method named SPaRKLE that seamlessly integrates symbolic and numerical techniques, leveraging the PCA heuristic to capture implicit knowledge and enrich KGs. We empirically compare SPaRKLE with state-of-the-art KG embedding and symbolic models, using established benchmarks. Our experimental outcomes underscore the efficacy of this hybrid approach, as it harnesses the strengths of both paradigms. SPaRKLE is publicly available on GitHub1.
- Fotis Aisopos, Samaneh Jozashoori, Emetis Niazmand, Disha Purohit, Ariam Rivas, Ahmad Sakor, Enrique Iglesias, Dimitrios Vogiatzis, Ernestina Menasalvas, Alejandro Rodríguez González, Guillermo Vigueras, Daniel Gómez-Bravo, Maria Torrente, Roberto Hernández López, Mariano Provencio Pulla, Athanasios Dalianis, Anna Triantafillou, Georgios Paliouras, and Maria-Esther Vidal. 2023. Knowledge graphs for enhancing transparency in health data ecosystems. Semantic Web 14, 5 (2023), 943–976. https://doi.org/10.3233/SW-223294Google ScholarCross Ref
- Farahnaz Akrami, Lingbing Guo, Wei Hu, and Chengkai Li. 2018. Re-evaluating Embedding-Based Knowledge Graph Completion Methods. In CIKM. https://doi.org/10.1145/3269206.3269266Google ScholarDigital Library
- Farahnaz Akrami, Mohammed Samiul Saeef, Qingheng Zhang, Wei Hu, and Chengkai Li. 2020. Realistic Re-Evaluation of Knowledge Graph Completion Methods: An Experimental Study. In Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data (Portland, OR, USA) (SIGMOD ’20). Association for Computing Machinery, New York, NY, USA, 1995–2010. https://doi.org/10.1145/3318464.3380599Google ScholarDigital Library
- Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt, Laurent Vermue, Mikhail Galkin, Sahand Sharifzadeh, Asja Fischer, Volker Tresp, and Jens Lehmann. 2020. Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework. CoRR (2020).Google Scholar
- Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt, Laurent Vermue, Sahand Sharifzadeh, Volker Tresp, and Jens Lehmann. 2021. PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings. Journal of Machine Learning Research (2021). http://jmlr.org/papers/v22/20-825.htmlGoogle Scholar
- Anna Breit, Laura Waltersdorfer, Fajar J. Ekaputra, Marta Sabou, Andreas Ekelhart, Andreea Iana, Heiko Paulheim, Jan Portisch, Artem Revenko, Annette Ten Teije, and Frank Van Harmelen. 2023. Combining Machine Learning and Semantic Web: A Systematic Mapping Study. ACM Comput. Surv. 55, 14s, Article 313 (jul 2023), 41 pages. https://doi.org/10.1145/3586163Google ScholarDigital Library
- Yashrajsinh Chudasama, Disha Purohit, Philipp D. Rohde, Julian Gercke, and Maria-Esther Vidal. 2023. InterpretME: A Tool for Interpretations of Machine Learning Models Over Knowledge Graphs. Semantic Web Journal. Special Issue on Tools & Systems (2023).Google Scholar
- Claudio Gutierrez and Juan F. Sequeda. 2021. Knowledge graphs. Commun. ACM 64, 3 (2021), 96–104. https://doi.org/10.1145/3418294Google ScholarDigital Library
- Nicholas Halliwell, Fabien Gandon, and Freddy Lecue. 2021. User Scored Evaluation of Non-Unique Explanations for Relational Graph Convolutional Network Link Prediction on Knowledge Graphs. In K-CAP. ACM.Google Scholar
- Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia d’Amato, Gerard de Melo, Claudio Gutierrez, Sabrina Kirrane, José Emilio Labra Gayo, Roberto Navigli, Sebastian Neumaier, Axel-Cyrille Ngonga Ngomo, Axel Polleres, Sabbir M. Rashid, Anisa Rula, Lukas Schmelzeisen, Juan Sequeda, Steffen Staab, and Antoine Zimmermann. 2021. Knowledge Graphs. Morgan & Claypool Publishers.Google Scholar
- Stanley Kok and Pedro M. Domingos. 2007. Statistical predicate invention. In ICML. https://doi.org/10.1145/1273496.1273551Google ScholarDigital Library
- Jonathan Lajus, Luis Galárraga, and Fabian Suchanek. 2020. Fast and Exact Rule Mining with AMIE 3. In The Semantic Web.Google Scholar
- Yann Loyer and Umberto Straccia. 2005. Any-world assumptions in logic programming. Theoretical Computer Science 342, 2 (2005), 351–381. https://doi.org/10.1016/j.tcs.2005.04.005Google ScholarDigital Library
- Farzaneh Mahdisoltani, Joanna Biega, and Fabian M. Suchanek. 2015. YAGO3: A Knowledge Base from Multilingual Wikipedias. In CIDR. http://cidrdb.org/cidr2015/Papers/CIDR15_Paper1.pdfGoogle Scholar
- Christian Meilicke, Melisachew Wudage Chekol, Daniel Ruffinelli, and Heiner Stuckenschmidt. 2019. Anytime Bottom-Up Rule Learning for Knowledge Graph Completion. In IJCAI-19. https://doi.org/10.24963/ijcai.2019/435Google ScholarCross Ref
- George A. Miller. 1995. WordNet: A Lexical Database for English. Commun. ACM (1995). https://doi.org/10.1145/219717.219748Google ScholarDigital Library
- Armita Khajeh Nassiri, Nathalie Pernelle, and Fatiha Saïs. 2023. REGNUM: Generating Logical Rules with Numerical Predicates in Knowledge Graphs. In The Semantic Web - 20th International Conference, ESWC 2023, Hersonissos, Crete, Greece, May 28 - June 1, 2023, Proceedings, Vol. 13870. Springer, 139–155. https://doi.org/10.1007/978-3-031-33455-9_9Google ScholarDigital Library
- Ariam Rivas, Diego Collarana, Maria Torrente, and Maria-Esther Vidal. 2023. A neuro-symbolic system over knowledge graphs for link prediction. Semantic Web Journal. Special Issue on Neuro-Symbolic Artificial Intelligence and the Semantic Web (2023), 1–25. https://doi.org/10.3233/SW-233324Google ScholarCross Ref
- Annette ten Teije and Frank van Harmelen. 2023. Architectural Patterns for Neuro-Symbolic AI. In Compendium of Neurosymbolic Artificial Intelligence, Pascal Hitzler, Md. Kamruzzaman Sarker, and Aaron Eberhart (Eds.). Frontiers in Artificial Intelligence and Applications, Vol. 369. IOS Press, 64–76. https://doi.org/10.3233/FAIA230135Google ScholarCross Ref
- Michael van Bekkum, Maaike de Boer, Frank van Harmelen, André Meyer-Vitali, and Annette ten Teije. 2021. Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases. CoRR (2021).Google ScholarDigital Library
- Roderick van der Weerdt, Victor de Boer, Laura Daniele, Ronald Siebes, and Frank van Harmelen. 2023. Evaluating the Effect of Semantic Enrichment on Entity Embeddings of IoT Knowledge Graphs. In Proceedings of the First International Workshop on Semantic Web on Constrained Things co-located with 20th Extended Semantic Web Conference, SWoCoT@ESWC 2023, Hersonissos, Greece, May 28, 2023(CEUR Workshop Proceedings, Vol. 3412), Ghislain Auguste Atemezing, Lionel Médini, and Frédérique Laforest (Eds.). CEUR-WS.org, 61–73.Google Scholar
- Laura Waltersdorfer, Anna Breit, Fajar J. Ekaputra, Marta Sabou, Andreas Ekelhart, Andreea Iana, Heiko Paulheim, Jan Portisch, Artem Revenko, Annette ten Teije, and Frank van Harmelen. 2023. Semantic Web Machine Learning Systems: An Analysis of System Patterns. In Compendium of Neurosymbolic Artificial Intelligence, Pascal Hitzler, Md. Kamruzzaman Sarker, and Aaron Eberhart (Eds.). Frontiers in Artificial Intelligence and Applications, Vol. 369. IOS Press, 77–99. https://doi.org/10.3233/FAIA230136Google ScholarCross Ref
Index Terms
- SPaRKLE : Symbolic caPtuRing of knowledge for Knowledge graph enrichment with LEarning
Recommendations
Knowledge Graph Completion by Context-Aware Convolutional Learning with Multi-Hop Neighborhoods
CIKM '18: Proceedings of the 27th ACM International Conference on Information and Knowledge ManagementThe main focus of relational learning for knowledge graph completion (KGC) lies in exploiting rich contextual information for facts. Many state-of-the-art models incorporate fact sequences, entity types, and even textual information. Unfortunately, most ...
Knowledge graph embedding methods for entity alignment: experimental review
AbstractIn recent years, we have witnessed the proliferation of knowledge graphs (KG) in various domains, aiming to support applications like question answering, recommendations, etc. A frequent task when integrating knowledge from different KGs is to ...
Knowledge Graph Entity Typing with Contrastive Learning
ICMLSC '22: Proceedings of the 2022 6th International Conference on Machine Learning and Soft ComputingKnowledge graph entity typing is an important way to complete knowledge graphs (KGs), aims at predicting the associating types of certain given entities. However, previous methods suppose that many (entity, entity type) pairs can be obtained for each ...
Comments