LightEA: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagation
This work addresses scalability and interpretability challenges in entity alignment for knowledge graph integration, offering a non-neural alternative that is incremental in its approach.
The paper tackled the problem of entity alignment between knowledge graphs by addressing scalability and interpretability issues in existing GNN-based methods, proposing LightEA, which achieved comparable or better results than state-of-the-art methods with only a tenth of the time consumption.
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.