A Simple Temporal Information Matching Mechanism for Entity Alignment Between Temporal Knowledge Graphs

TL;DR

This paper introduces a simple GNN-based approach with a temporal matching mechanism for entity alignment in temporal knowledge graphs, outperforming existing methods while reducing complexity and enabling unsupervised seed generation.

Contribution

It proposes a novel, less complex GNN model that leverages a temporal information matching mechanism and an unsupervised seed generation method for entity alignment in TKGs.

Findings

Supervised method outperforms previous approaches.

Unsupervised seed generation achieves competitive results.

Model is more efficient with fewer parameters.

Abstract

Entity alignment (EA) aims to find entities in different knowledge graphs (KGs) that refer to the same object in the real world. Recent studies incorporate temporal information to augment the representations of KGs. The existing methods for EA between temporal KGs (TKGs) utilize a time-aware attention mechanism to incorporate relational and temporal information into entity embeddings. The approaches outperform the previous methods by using temporal information. However, we believe that it is not necessary to learn the embeddings of temporal information in KGs since most TKGs have uniform temporal representations. Therefore, we propose a simple graph neural network (GNN) model combined with a temporal information matching mechanism, which achieves better performance with less time and fewer parameters. Furthermore, since alignment seeds are difficult to label in real-world applications, we also propose a method to generate unsupervised alignment seeds via the temporal information of TKG. Extensive experiments on public datasets indicate that our supervised method significantly outperforms the previous methods and the unsupervised one has competitive performance.