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

TL;DR

RCTEA introduces a novel framework for Temporal Entity Alignment that effectively combines structural and temporal features using a richness-guided attention mechanism and neighborhood consensus, achieving state-of-the-art results.

Contribution

The paper proposes RCTEA, a new method that jointly models structural and temporal features with adaptive weighting and consensus algorithms for improved entity alignment.

Findings

Achieves state-of-the-art performance on public TEA benchmarks.

Effectively fuses structural and temporal features with richness-guided attention.

Robustly aligns entities despite noisy contexts using neighborhood consensus.

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.