A Simple Temporal Information Matching Mechanism for Entity Alignment Between Temporal Knowledge Graphs
This work addresses entity alignment in temporal knowledge graphs, offering a more efficient solution for applications where labeled data is scarce, though it is incremental in nature.
The paper tackles entity alignment between temporal knowledge graphs by proposing a simple GNN model with a temporal information matching mechanism, achieving better performance with less time and fewer parameters, and also introduces an unsupervised method for generating alignment seeds that shows competitive results.
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.