RCTEA: Richness-guided Co-training for Temporal Entity Alignment

2026-05-18

AI Summary

Existing approaches to entity alignment in temporal knowledge graphs struggle to effectively integrate structural and temporal features and often overlook the impact of node informativeness on feature propagation. To address these limitations, this work proposes the RCTEA framework, which jointly models structural and temporal characteristics through an informativeness-guided attention mechanism and an adaptive weighting strategy, enabling complementary synergy between the two feature types. Furthermore, a dual-view neighborhood consensus algorithm is introduced to enhance local structural consistency, thereby improving alignment robustness. Extensive experiments on multiple public benchmarks demonstrate that RCTEA significantly outperforms state-of-the-art methods, achieving new best performance.

Abstract

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.

Problem

• Temporal Entity Alignment
• Temporal Knowledge Graphs
• Information Richness
• Feature Fusion
• Entity Alignment

Innovation

• Temporal Entity Alignment
• Richness-guided Attention
• Dual-view Neighborhood Consensus
• Feature Fusion
• Temporal Knowledge Graphs