Abstract
Knowledge Graph (KG) embedding methods represent KG entities as vectors in an embedding space, and they have been successfully used for a variety of tasks, including link prediction and entity classification. While some of the recent embedding methods outperform traditional approaches on these tasks, their main drawback is the lack of interpretability. Several methods for explaining predictions made by KG embeddings have been proposed in the literature. However, none of them targeted the problem of constructing model explanations for embeddings, i.e., interpretable KG representations that behave similarly to embeddings on certain tasks. We address this problem and propose a novel method for generating interpretable vectors for entity embeddings. To achieve this, we employ embedded feature selection techniques to extract from the KG, on which the embedding model was trained, propositional features that are important for a given KG embedding model. Our approach sheds light on the information in the KG captured by embeddings and provides valuable insights that can be used to further enhance the embedding models. Additionally, we demonstrate the usefulness of our method for explaining embedding-based entity similarity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: ISWC/ASWC, pp. 722–735 (2007)
Baader, F., Calvanese, D., McGuinness, D., Patel-Schneider, P., Nardi, D., et al.: The Description Logic Handbook: Theory, Implementation and Applications. Cambridge University Press (2003)
Betz, P., Meilicke, C., Stuckenschmidt, H.: Adversarial explanations for knowledge graph embeddings. In: Raedt, L.D. (ed.) IJCAI 2022, pp. 2820–2826 (2022)
Bhatt, U., Xiang, A., Shubham Sharma, t.: Explainable machine learning in deployment. In: FAT* 2020, pp. 648–657 (2020)
Bollacker, K., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: Freebase: a collaboratively created graph database for structuring human knowledge. In: SIGMOD 2008, pp. 1247–1250 (2008)
Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NeurIPs, pp. 2787–2795 (2013)
Chandrahas, Sengupta, T., Pragadeesh, C., Talukdar, P.P.: Inducing interpretability in knowledge graph embeddings. In: Bhattacharyya, P., Sharma, D.M., Sangal, R. (eds.) ICON 2020, pp. 70–75 (2020)
Cheng, W., Kasneci, G., Graepel, T., Stern, D.H., Herbrich, R.: Automated feature generation from structured knowledge. In: CIKM, 2011, pp. 1395–1404 (2011)
Costabello, L., et al.: On explainable AI: from theory to motivation, applications and limitations. In: A Tutorial at AAAI 2019 (2019)
Cover, T.M., Hart, P.E.: Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13(1), 21–27 (1967)
Galárraga, L.: Effects of locality and rule language on explanations for knowledge graph embeddings. CoRR abs/2302.06967 (2023)
Galkin, M., Denis, E.G., Wu, J., Hamilton, W.L.: NodePiece: compositional and parameter-efficient representations of large knowledge graphs. In: ICLR 2022 (2022)
Gusmão, A.C., Correia, A.H.C., Bona, G.D., Cozman, F.G.: Interpreting embedding models of knowledge bases: a pedagogical approach. CoRR abs/1806.09504 (2018)
Halliwell, N., Gandon, F., Lécué, F.: User scored evaluation of non-unique explanations for relational graph convolutional network link prediction on knowledge graphs. In: K-CAP, pp. 57–64 (2021)
Haykin, S.: Neural Networks: A Comprehensive Foundation (1994)
Ho, V.T., Stepanova, D., Gad-Elrab, M.H., Kharlamov, E., Weikum, G.: Rule Learning from Knowledge Graphs Guided by Embedding Models. In: Vrandečić, D., Bontcheva, K., Suárez-Figueroa, M.C., Presutti, V., Celino, I., Sabou, M., Kaffee, L.-A., Simperl, E. (eds.) ISWC 2018. LNCS, vol. 11136, pp. 72–90. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00671-6_5
Jain, N., Kalo, J.C., Balke, W.T., Krestel, R.: Do embeddings actually capture knowledge graph semantics? In: ESWC (2021)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR 2017 (2017)
Krogel, M., Rawles, S.A., Zelezný, F., Flach, P.A., Lavrac, N., Wrobel, S.: In: ILP 2003, vol. 2835, pp. 197–214 (2003)
Lajus, J., Galárraga, L., Suchanek, F.: Fast and exact rule mining with AMIE 3. In: Harth, A., et al. (eds.) ESWC 2020. LNCS, vol. 12123, pp. 36–52. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-49461-2_3
Lavrač, N., Škrlj, B., Robnik-Šikonja, M.: Propositionalization and embeddings: two sides of the same coin. Mach. Learn. 109(7), 1465–1507 (2020)
Lawler, I., Sullivan, E.: Model explanation versus model-induced explanation. Found. Sci. 26, 1049–1074 (2021)
Meilicke, C., Chekol, M.W., Ruffinelli, D., Stuckenschmidt, H.: Anytime bottom-up rule learning for knowledge graph completion. In: IJCAI 2019, pp. 3137–3143 (2019)
Mežnar, S., Lavrač, N., Škrlj, B.: Snore: scalable unsupervised learning of symbolic node representations. IEEE Access 8, 212568–212588 (2020)
Nandwani, Y., Gupta, A., Agrawal, A., Chauhan, M.S., Singla, P., Mausam: OXKBC: outcome explanation for factorization based knowledge base completion. In: AKBC 2020 (2020)
Nguyen, D.Q., Nguyen, T.D., Nguyen, D.Q., Phung, D.Q.: A novel embedding model for knowledge base completion based on convolutional neural network. In: NAACL (2018)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Pellegrino, M.A., Altabba, A., Garofalo, M., Ristoski, P., Cochez, M.: GEval: a modular and extensible evaluation framework for graph embedding techniques. In: Harth, A., et al. (eds.) ESWC 2020. LNCS, vol. 12123, pp. 565–582. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-49461-2_33
Portisch, J., Heist, N., Paulheim, H.: Knowledge graph embedding for data mining vs. knowledge graph embedding for link prediction - two sides of the same coin? Semant. Web 13(3), 399–422 (2022)
Ristoski, P., Paulheim, H.: A comparison of propositionalization strategies for creating features from linked open data. In: Tiddi, I., d’Aquin, M., Jay, N. (eds.) LOD Workshop at ECML PKDD 2014 (2014)
Ristoski, P., Rosati, J., Noia, T.D., Leone, R.D., Paulheim, H.: RDF2Vec: RDF graph embeddings and their applications. Semant. Web 10(4), 721–752 (2019)
Rossi, A., Firmani, D., Merialdo, P., Teofili, T.: Explaining link prediction systems based on knowledge graph embeddings. In: SIGMOD 2022, pp. 2062–2075 (2022)
Segal, M., Xiao, Y.: Multivariate random forests. WIREs Data Min. Knowl. Disc. 1, 80–87 (2011)
Shi, B., Weninger, T.: Open-world knowledge graph completion. ArXiv abs/1711.03438 (2018)
Steenwinckel, B., Vandewiele, G., Weyns, M., Agozzino, T., Turck, F.D., Ongenae, F.: INK: knowledge graph embeddings for node classification. Data Min. Knowl. Discov. 36(2), 620–667 (2022)
Suchanek, F.M., Kasneci, G., Weikum, G.: Yago: A core of semantic knowledge. In: WWW 2007 (2007)
Tang, J., et al.: Computational advances of tumor marker selection and sample classification in cancer proteomics. Comput. Struct. Biotechnol. J. 18, 2012–2025 (2020)
Toutanova, K., Chen, D.: Observed versus latent features for knowledge base and text inference. In: Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality (2015)
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., Bouchard, G.: Complex embeddings for simple link prediction. In: ICML, pp. 2071–2080 (2016)
Vashishth, S., Sanyal, S., Nitin, V., Talukdar, P.P.: Composition-based multi-relational graph convolutional networks. In: ICLR 2020 (2020)
Wang, Q., Mao, Z., Wang, B., Guo, L.: Knowledge graph embedding: a survey of approaches and applications. IEEE Trans. Knowl. Data Eng. 29(12), 2724–2743 (2017)
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? CoRR abs/1810.00826 (2018)
Yang, B., Yih, W., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. In: ICLR (2015)
Yogatama, D., Gillick, D., Lazic, N.: Embedding methods for fine grained entity type classification. In: ACL 2015, pp. 291–296 (2015)
Zhang, W., et al.: Iteratively learning embeddings and rules for knowledge graph reasoning. In: WWW 2019, pp. 2366–2377 (2019)
Zhao, Y., Zhang, A., Xie, R., Liu, K., Wang, X.: Connecting embeddings for knowledge graph entity typing. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J.R. (eds.) ACL 2020, pp. 6419–6428 (2020)
Zhu, Z., Zhang, Z., Xhonneux, L.A.C., Tang, J.: Neural bellman-ford networks: a general graph neural network framework for link prediction. In: NeurIPS 2021, pp. 29476–29490 (2021)
Acknowledgements
We thank anonymous reviews for their useful feedback, and Dr. Blaž Škrlj for helpful comments on the initial version of this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ismaeil, Y., Stepanova, D., Tran, TK., Blockeel, H. (2023). FeaBI: A Feature Selection-Based Framework for Interpreting KG Embeddings. In: Payne, T.R., et al. The Semantic Web – ISWC 2023. ISWC 2023. Lecture Notes in Computer Science, vol 14265. Springer, Cham. https://doi.org/10.1007/978-3-031-47240-4_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-47240-4_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47239-8
Online ISBN: 978-3-031-47240-4
eBook Packages: Computer ScienceComputer Science (R0)