RCTEA: Richness-guided Co-training for Temporal Entity Alignment
For researchers integrating temporal knowledge graphs, RCTEA provides a more accurate alignment method by leveraging information richness and robust feature fusion.
RCTEA addresses temporal entity alignment in temporal knowledge graphs by jointly modeling structural and temporal features with a richness-guided attention mechanism and dual-view neighborhood consensus, achieving state-of-the-art performance on public benchmarks.
Temporal Entity Alignment (TEA), which aims to identify equivalent entities across Temporal Knowledge Graphs (TKGs), is crucial for integrating knowledge facts from multiple sources. However, existing TEA models often fail to capture the orthogonal yet complementary effects between structural and temporal features, and typically overlook the importance of information richness, a key factor for effective message passing in neural feature encoders. To address these limitations, we propose the RCTEA framework, which jointly models both structural and temporal aspects of TKGs for entity alignment. Specifically, we design a richness-guided attention mechanism along with an adaptive weighting strategy to facilitate effective feature fusion. To ensure robust alignment despite noisy entity contexts, we introduce a dual-view neighborhood consensus algorithm that jointly refines the feature encoders to enforce local structural consistency of the predicted alignments. Extensive experiments demonstrate the superiority of RCTEA, achieving state-of-the-art performance on public TEA benchmarks.