Research map / Graph learning / Knowledge and temporal graphs
Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs
Ruijie Wang, zheng li, Dachun Sun, Shengzhong Liu, Jinning Li, Bing Yin, Tarek Abdelzaher
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add temporal meta-learning instead of MetaDyGNN | MetaTKGR · YAGO 3-shot | MRR: 0.350 -> 0.370 | Improved |
| temporal meta-learning vs MetaDyGNN | MetaTKGR · WIKI 3-shot | MRR: 0.309 -> 0.329 | Improved |
| temporal meta-learning vs MetaDyGNN | MetaTKGR · ICEWS18 3-shot | MRR: 0.307 -> 0.335 | Improved |
| temporal meta-learning vs MetaDyGNN | MetaTKGR · YAGO 1-shot | MRR: 0.269 -> 0.294 | Improved |
| temporal meta-learning vs MetaDyGNN | MetaTKGR · ICEWS18 2-shot | MRR: 0.269 -> 0.300 | Improved |
| fine-tune on new entities instead of meta-learning (ablation) | MetaTKGR · YAGO/ICEWS18 | H@10 | Hurt |
| use conventional static MAML instead of temporal meta-learning (ablation) | MetaTKGR · YAGO/ICEWS18 | H@10 | Hurt |
| remove temporal adaptation regularizer (ablation) | MetaTKGR · YAGO/ICEWS18 | H@10 | Hurt |
| vary number of shots used during meta-training (ablation) | MetaTKGR · TKG benchmarks | MRR | No clear effect |
| more shots at test time | MetaTKGR · TKG benchmarks | MRR | Improved |
Closest papers by meaning
- Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning (NeurIPS 2024 · similarity 0.89)
- TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs (NeurIPS 2024 · similarity 0.89)
- TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning (AAAI 2024 · similarity 0.87)
- CognTKE: A Cognitive Temporal Knowledge Extrapolation Framework (AAAI 2025 · similarity 0.87)
- DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach (NeurIPS 2024 · similarity 0.87)
- Interpreting Temporal Knowledge Graph Reasoning (Student Abstract) (AAAI 2024 · similarity 0.87)
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.
