Research map / Graph learning / Knowledge and temporal graphs
Temporal Knowledge Graph Reasoning with Historical Contrastive Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| jointly model historical and non-historical dependencies with contrastive learning and mask-based inference | CENET · ICEWS18 | Hits@1: 43.51 -> 47.10 | Helped |
| jointly model historical and non-historical dependencies with contrastive learning and mask-based inference | CENET · ICEWS14 | Hits@1: 45.73 -> 49.61 | Helped |
| jointly model historical and non-historical dependencies with contrastive learning and mask-based inference | CENET · GDELT | Hits@1: 46.35 -> 55.99 | Helped |
| jointly model historical and non-historical dependencies with contrastive learning and mask-based inference | CENET · WIKI | Hits@1: 57.43 -> 68.33 | Helped |
| jointly model historical and non-historical dependencies with contrastive learning and mask-based inference | CENET · YAGO | Hits@1: 67.05 -> 84.03 | Helped |
| add historical and non-historical dependencies together rather than retaining historical dependency alone (ablation) | CENET · ICEWS18 | Hits@1: 47.15 -> 47.10 | Mixed |
| add historical and non-historical dependencies together rather than retaining historical dependency alone (ablation) | CENET · YAGO | Hits@1: 70.24 -> 84.03 | Helped |
| add supervised contrastive loss (stage 1) (ablation) | CENET · ICEWS18 | Hits@1: 46.47 -> 47.10 | Helped |
| add supervised contrastive loss (stage 1) (ablation) | CENET · YAGO | Hits@1: 73.96 -> 84.03 | Helped |
| add binary-classifier training and mask-based inference (ablation) | CENET · ICEWS18 | Hits@1: 46.30 -> 47.10 | Helped |
| add binary-classifier training and mask-based inference (ablation) | CENET · YAGO | Hits@1: 76.12 -> 84.03 | Helped |
| add historical contrastive learning (ablation) | CENET · ICEWS18 | Hits@1: 45.89 -> 47.10 | Helped |
Closest papers by meaning
- TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning (AAAI 2024 · similarity 0.88)
- DPCL-Diff：Temporal Knowledge Graph Reasoning Based on Graph Node Diffusion Model with Dual-Domain Periodic Contrastive Learning (AAAI 2025 · similarity 0.87)
- Interpreting Temporal Knowledge Graph Reasoning (Student Abstract) (AAAI 2024 · similarity 0.86)
- Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning (NeurIPS 2024 · similarity 0.85)
- TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs (NeurIPS 2024 · similarity 0.84)
- CognTKE: A Cognitive Temporal Knowledge Extrapolation Framework (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.