Unsupervised Entity Alignment Based on Personalized Discriminative Rooted Tree

TL;DR

This paper introduces UNEA, an unsupervised entity alignment method that creates personalized entity embeddings using rooted tree sampling and attention, and employs mutual information maximization to improve alignment accuracy across knowledge graphs.

Contribution

The paper proposes a novel unsupervised EA approach combining personalized tree-based embeddings and mutual information regularization, outperforming existing methods.

Findings

Achieves state-of-the-art results in unsupervised entity alignment.

Outperforms many supervised EA baselines.

Effective in reducing distribution distortion between KGs.

Abstract

Entity Alignment (EA) is to link potential equivalent entities across different knowledge graphs (KGs). Most existing EA methods are supervised as they require the supervision of seed alignments, i.e., manually specified aligned entity pairs. Very recently, several EA studies have made some attempts to get rid of seed alignments. Despite achieving preliminary progress, they still suffer two limitations: (1) The entity embeddings produced by their GNN-like encoders lack personalization since some of the aggregation subpaths are shared between different entities. (2) They cannot fully alleviate the distribution distortion issue between candidate KGs due to the absence of the supervised signal. In this work, we propose a novel unsupervised entity alignment approach called UNEA to address the above two issues. First, we parametrically sample a tree neighborhood rooted at each entity, and accordingly develop a tree attention aggregation mechanism to extract a personalized embedding for each entity. Second, we introduce an auxiliary task of maximizing the mutual information between the input and the output of the KG encoder, to regularize the model and prevent the distribution distortion. Extensive experiments show that our UNEA achieves a new state-of-the-art for the unsupervised EA task, and can even outperform many existing supervised EA baselines.