An Effective and Efficient Time-aware Entity Alignment Framework via Two-aspect Three-view Label Propagation
This work addresses the problem of efficiently aligning entities in temporal knowledge graphs for knowledge fusion, offering a scalable solution that is incremental over prior neural approaches.
The paper tackles the scalability issue of existing time-aware entity alignment methods based on Graph Neural Networks by proposing LightTEA, a non-neural framework that significantly outperforms state-of-the-art methods on public datasets while reducing time consumption to at most dozens of seconds, less than 10% of the most efficient existing method.
Entity alignment (EA) aims to find the equivalent entity pairs between different knowledge graphs (KGs), which is crucial to promote knowledge fusion. With the wide use of temporal knowledge graphs (TKGs), time-aware EA (TEA) methods appear to enhance EA. Existing TEA models are based on Graph Neural Networks (GNN) and achieve state-of-the-art (SOTA) performance, but it is difficult to transfer them to large-scale TKGs due to the scalability issue of GNN. In this paper, we propose an effective and efficient non-neural EA framework between TKGs, namely LightTEA, which consists of four essential components: (1) Two-aspect Three-view Label Propagation, (2) Sparse Similarity with Temporal Constraints, (3) Sinkhorn Operator, and (4) Temporal Iterative Learning. All of these modules work together to improve the performance of EA while reducing the time consumption of the model. Extensive experiments on public datasets indicate that our proposed model significantly outperforms the SOTA methods for EA between TKGs, and the time consumed by LightTEA is only dozens of seconds at most, no more than 10% of the most efficient TEA method.