Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining

TL;DR

This paper introduces Dual-AMN, a novel entity alignment method that significantly improves speed and accuracy in multi-source Knowledge Graphs by using a dual attention encoder and normalized hard sample mining, outperforming previous methods.

Contribution

The paper presents a new KG encoder and a hard sample mining loss to enhance efficiency and accuracy in entity alignment tasks, especially on large datasets.

Findings

Achieves at least 10 times faster processing on DWY100K.

Outperforms previous methods in accuracy metrics across datasets.

Reduces computational complexity while maintaining high performance.

Abstract

Seeking the equivalent entities among multi-source Knowledge Graphs (KGs) is the pivotal step to KGs integration, also known as \emph{entity alignment} (EA). However, most existing EA methods are inefficient and poor in scalability. A recent summary points out that some of them even require several days to deal with a dataset containing 200,000 nodes (DWY100K). We believe over-complex graph encoder and inefficient negative sampling strategy are the two main reasons. In this paper, we propose a novel KG encoder -- Dual Attention Matching Network (Dual-AMN), which not only models both intra-graph and cross-graph information smartly, but also greatly reduces computational complexity. Furthermore, we propose the Normalized Hard Sample Mining Loss to smoothly select hard negative samples with reduced loss shift. The experimental results on widely used public datasets indicate that our method achieves both high accuracy and high efficiency. On DWY100K, the whole running process of our method could be finished in 1,100 seconds, at least 10* faster than previous work. The performances of our method also outperform previous works across all datasets, where Hits@1 and MRR have been improved from 6% to 13%.