TY - GEN
T1 - LightEA
T2 - 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
AU - Mao, Xin
AU - Wang, Wenting
AU - Wu, Yuanbin
AU - Lan, Man
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - Entity Alignment (EA) aims to find equivalent entity pairs between KGs, which is the core step of bridging and integrating multi-source KGs. In this paper, we argue that existing GNN-based EA methods inherit the inborn defects from their neural network lineage: weak scalability and poor interpretability. Inspired by recent studies, we reinvent the Label Propagation algorithm to effectively run on KGs and propose a non-neural EA framework - LightEA, consisting of three efficient components: (i) Random Orthogonal Label Generation, (ii) Three-view Label Propagation, and (iii) Sparse Sinkhorn Iteration. According to the extensive experiments on public datasets, LightEA has impressive scalability, robustness, and interpretability. With a mere tenth of time consumption, LightEA achieves comparable results to state-of-the-art methods across all datasets and even surpasses them on many.
AB - Entity Alignment (EA) aims to find equivalent entity pairs between KGs, which is the core step of bridging and integrating multi-source KGs. In this paper, we argue that existing GNN-based EA methods inherit the inborn defects from their neural network lineage: weak scalability and poor interpretability. Inspired by recent studies, we reinvent the Label Propagation algorithm to effectively run on KGs and propose a non-neural EA framework - LightEA, consisting of three efficient components: (i) Random Orthogonal Label Generation, (ii) Three-view Label Propagation, and (iii) Sparse Sinkhorn Iteration. According to the extensive experiments on public datasets, LightEA has impressive scalability, robustness, and interpretability. With a mere tenth of time consumption, LightEA achieves comparable results to state-of-the-art methods across all datasets and even surpasses them on many.
UR - https://www.scopus.com/pages/publications/85149436405
U2 - 10.18653/v1/2022.emnlp-main.52
DO - 10.18653/v1/2022.emnlp-main.52
M3 - 会议稿件
AN - SCOPUS:85149436405
T3 - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
SP - 825
EP - 838
BT - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
A2 - Goldberg, Yoav
A2 - Kozareva, Zornitsa
A2 - Zhang, Yue
PB - Association for Computational Linguistics (ACL)
Y2 - 7 December 2022 through 11 December 2022
ER -