A Self-supervised Method for Entity Alignment

Abstract

Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing large-scale KGs. Over the course of its development, supervision has been considered necessary for accurate alignments. Inspired by the recent progress of self-supervised learning, we explore the extent to which we can get rid of supervision for entity alignment. Existing supervised methods for this task focus on pulling each pair of positive (labeled) entities close to each other. However, our analysis suggests that the learning of entity alignment can actually benefit more from pushing sampled (unlabeled) negatives far away than pulling positive aligned pairs close. We present SelfKG by leveraging this discovery to design a contrastive learning strategy across two KGs. Extensive experiments on benchmark datasets demonstrate that SelfKG without supervision can match or achieve comparable results with state-of-the-art supervised baselines. The performance of SelfKG demonstrates self-supervised learning offers great potential for entity alignment in KGs.

arXiv commentFor further update, modification and certificate application

References in corpus (10)

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Graph Contrastive Learning with Augmentations
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
• Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding
• Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
• Multi-Channel Graph Neural Network for Entity Alignment
• LinkNBed: Multi-Graph Representation Learning with Entity Linkage
• Jointly Learning Entity and Relation Representations for Entity Alignment
• Aligning Cross-Lingual Entities with Multi-Aspect Information