From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment

Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual KGs, which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are proposed and show decent performance improvements on several public datasets. Meanwhile, existing GNN-based EA methods inevitably inherit poor interpretability and low efficiency from neural networks. Motivated by the isomorphic assumption of GNNbased methods, we successfully transform the cross-lingual EA problem into the assignment problem. Based on this finding, we propose a frustratingly Simple but Effective Unsupervised entity alignment method (SEU) without neural networks. Extensive experiments show that our proposed unsupervised method even beats advanced supervised methods across all public datasets and has high efficiency, interpretability, and stability.

[1]  Jiuyang Tang,et al.  An Experimental Study of State-of-the-Art Entity Alignment Approaches , 2020, IEEE Transactions on Knowledge and Data Engineering.

[2]  Dan Roth,et al.  Cross-lingual Entity Alignment with Incidental Supervision , 2021, EACL.

[3]  Harold W. Kuhn,et al.  The Hungarian method for the assignment problem , 1955, 50 Years of Integer Programming.

[4]  Bernardo Cuenca Grau,et al.  LogMap: Logic-Based and Scalable Ontology Matching , 2011, SEMWEB.

[5]  Zhichun Wang,et al.  Knowledge Graph Alignment with Entity-Pair Embedding , 2020, EMNLP.

[6]  Zhichun Wang,et al.  Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks , 2018, EMNLP.

[7]  Richard Sinkhorn.  A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices , 1964 .

[8]  Robert E. Tarjan,et al.  On Minimum-Cost Assignments in Unbalanced Bipartite Graphs , 2012 .

[9]  Jiaoyan Chen,et al.  An Industry Evaluation of Embedding-based Entity Alignment , 2020, COLING.

[10]  Xiang Zhao,et al.  Degree-Aware Alignment for Entities in Tail , 2020, SIGIR.

[11]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[12]  Yuting Wu,et al.  Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs , 2019, IJCAI.

[13]  Xiaolong Jin,et al.  Stepwise Reasoning for Multi-Relation Question Answering over Knowledge Graph with Weak Supervision , 2020, WSDM.

[14]  Dongyan Zhao,et al.  Jointly Learning Entity and Relation Representations for Entity Alignment , 2019, EMNLP.

[15]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[16]  Zhiyuan Liu,et al.  Exploring and Evaluating Attributes, Values, and Structure for Entity Alignment , 2020, EMNLP.

[17]  Wei Hu,et al.  Bootstrapping Entity Alignment with Knowledge Graph Embedding , 2018, IJCAI.

[18]  Jimmy J. Lin,et al.  Aligning Cross-Lingual Entities with Multi-Aspect Information , 2019, EMNLP.

[19]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Jiuyang Tang,et al.  Collective Entity Alignment via Adaptive Features , 2020, 2020 IEEE 36th International Conference on Data Engineering (ICDE).

[21]  Wei Hu,et al.  Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding , 2017, SEMWEB.

[22]  Yansong Feng,et al.  Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network , 2019, ACL.

[23]  Nils M. Kriege,et al.  Deep Graph Matching Consensus , 2020, ICLR.

[24]  Yixin Cao,et al.  Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences , 2019, WWW.

[25]  Chen Zhao,et al.  Complex Factoid Question Answering with a Free-Text Knowledge Graph , 2020, WWW.

[26]  Scott W. Linderman,et al.  Learning Latent Permutations with Gumbel-Sinkhorn Networks , 2018, ICLR.

[27]  Serge Abiteboul,et al.  PARIS: Probabilistic Alignment of Relations, Instances, and Schema , 2011, Proc. VLDB Endow..

[28]  Wei Hu,et al.  Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs , 2019, ICML.

[29]  Marco Cuturi,et al.  Sinkhorn Distances: Lightspeed Computation of Optimal Transport , 2013, NIPS.

[30]  Wenting Wang,et al.  MRAEA: An Efficient and Robust Entity Alignment Approach for Cross-lingual Knowledge Graph , 2020, WSDM.

[31]  A. Volgenant,et al.  A shortest augmenting path algorithm for dense and sparse linear assignment problems , 1987, Computing.

[32]  Chengjiang Li,et al.  Multi-Channel Graph Neural Network for Entity Alignment , 2019, ACL.

[33]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[34]  Minyi Guo,et al.  Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation , 2019, WWW.

[35]  Ryan P. Adams,et al.  Ranking via Sinkhorn Propagation , 2011, ArXiv.