What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings

Zequn Sun, Jiacheng Huang, Xiaozhou Xu, Qijin Chen, Weijun Ren, Wei Hu
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32875-32885, 2023.

Abstract

Joint representation learning over multi-sourced knowledge graphs (KGs) yields transferable and expressive embeddings that improve downstream tasks. Entity alignment (EA) is a critical step in this process. Despite recent considerable research progress in embedding-based EA, how it works remains to be explored. In this paper, we provide a similarity flooding perspective to explain existing translation-based and aggregation-based EA models. We prove that the embedding learning process of these models actually seeks a fixpoint of pairwise similarities between entities. We also provide experimental evidence to support our theoretical analysis. We propose two simple but effective methods inspired by the fixpoint computation in similarity flooding, and demonstrate their effectiveness on benchmark datasets. Our work bridges the gap between recent embedding-based models and the conventional similarity flooding algorithm. It would improve our understanding of and increase our faith in embedding-based EA.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-sun23d, title = {What Makes Entities Similar? {A} Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings}, author = {Sun, Zequn and Huang, Jiacheng and Xu, Xiaozhou and Chen, Qijin and Ren, Weijun and Hu, Wei}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {32875--32885}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/sun23d/sun23d.pdf}, url = {https://proceedings.mlr.press/v202/sun23d.html}, abstract = {Joint representation learning over multi-sourced knowledge graphs (KGs) yields transferable and expressive embeddings that improve downstream tasks. Entity alignment (EA) is a critical step in this process. Despite recent considerable research progress in embedding-based EA, how it works remains to be explored. In this paper, we provide a similarity flooding perspective to explain existing translation-based and aggregation-based EA models. We prove that the embedding learning process of these models actually seeks a fixpoint of pairwise similarities between entities. We also provide experimental evidence to support our theoretical analysis. We propose two simple but effective methods inspired by the fixpoint computation in similarity flooding, and demonstrate their effectiveness on benchmark datasets. Our work bridges the gap between recent embedding-based models and the conventional similarity flooding algorithm. It would improve our understanding of and increase our faith in embedding-based EA.} }
Endnote
%0 Conference Paper %T What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings %A Zequn Sun %A Jiacheng Huang %A Xiaozhou Xu %A Qijin Chen %A Weijun Ren %A Wei Hu %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-sun23d %I PMLR %P 32875--32885 %U https://proceedings.mlr.press/v202/sun23d.html %V 202 %X Joint representation learning over multi-sourced knowledge graphs (KGs) yields transferable and expressive embeddings that improve downstream tasks. Entity alignment (EA) is a critical step in this process. Despite recent considerable research progress in embedding-based EA, how it works remains to be explored. In this paper, we provide a similarity flooding perspective to explain existing translation-based and aggregation-based EA models. We prove that the embedding learning process of these models actually seeks a fixpoint of pairwise similarities between entities. We also provide experimental evidence to support our theoretical analysis. We propose two simple but effective methods inspired by the fixpoint computation in similarity flooding, and demonstrate their effectiveness on benchmark datasets. Our work bridges the gap between recent embedding-based models and the conventional similarity flooding algorithm. It would improve our understanding of and increase our faith in embedding-based EA.
APA
Sun, Z., Huang, J., Xu, X., Chen, Q., Ren, W. & Hu, W.. (2023). What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:32875-32885 Available from https://proceedings.mlr.press/v202/sun23d.html.

Related Material