Research map / Graph learning / Knowledge and temporal graphs
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
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 |
|---|---|---|---|
| use CyGNet's copy-generation model instead of RE-NET | temporal link prediction · ICEWS18 | MRR: 42.93 -> 46.69 | Helped |
| use CyGNet's copy-generation model instead of RE-NET | temporal link prediction · ICEWS14 | MRR: 45.71 -> 48.63 | Helped |
| use CyGNet's copy-generation model instead of RE-NET | temporal link prediction · GDELT | MRR: 40.12 -> 50.92 | Helped |
| use CyGNet's copy-generation model instead of RE-NET | temporal link prediction · WIKI | MRR: 51.97 -> 45.50 | Hurt |
| use CyGNet's copy-generation model instead of RE-NET | temporal link prediction · YAGO | MRR: 65.16 -> 63.47 | Hurt |
| add Generation mode to the Copy-only model (ablation) | CyGNet on ICEWS18 · ICEWS18 | MRR: 42.60 -> 46.69 | Helped |
| add Copy mode to the Generation-only model (ablation) | CyGNet on ICEWS18 · ICEWS18 | MRR: 34.58 -> 46.69 | Helped |
| allow Generation mode to score historical-vocabulary entities (ablation) | CyGNet on ICEWS18 · ICEWS18 | MRR: 43.88 -> 46.69 | Helped |
| increase the copy weight within a certain range, but avoid over-weighting historical facts (ablation) | CyGNet on ICEWS18 · ICEWS18 | MRR | Mixed |
Closest papers by meaning
- TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning (AAAI 2024 · similarity 0.86)
- TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion (ICML 2025 · similarity 0.86)
- TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs (NeurIPS 2024 · similarity 0.85)
- Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning (NeurIPS 2024 · similarity 0.85)
- Interpreting Temporal Knowledge Graph Reasoning (Student Abstract) (AAAI 2024 · similarity 0.85)
- ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains (ICLR 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.