RCTEA: Richness-guided Co-training for Temporal Entity Alignment
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Temporal Entity Alignment | YAGO-WIKI50K 1K | MRR97.9 | 11 | |
| Temporal Entity Alignment | DICEWS 200 | MRR0.958 | 11 | |
| Temporal Entity Alignment | YAGO-WIKI180K 2000 seeds (All) | MRR46.8 | 10 | |
| Temporal Entity Alignment | YAGO-WIKI180K Non-tem (50.4%) 2000 seeds | MRR0.232 | 10 | |
| Temporal Entity Alignment | YAGO-WIKI180K Sparse-tem (43%) 2000 seeds | MRR66.9 | 10 | |
| Temporal Entity Alignment | YAGO-WIKI180K Dense-tem (6.6%) 2000 seeds | MRR97.1 | 10 | |
| Temporal Entity Alignment | BETA (10% seeds) | Hits@170.7 | 10 | |
| Temporal Entity Alignment | BETA (30% seeds) | H@172 | 10 | |
| Temporal Entity Alignment | DICEWS 1K | MRR96.1 | 10 | |
| Temporal Entity Alignment | YAGO-WIKI50K 5K | MRR98.7 | 10 |