Research map / Graph learning / Knowledge and temporal graphs
Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities
Ze Zhao, He Yuhui, Lyuwen Wu, Gu Tang, Bin Lu, Xiaoying Gan, Luoyi Fu, Xinbing Wang, Chenghu Zhou
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 codebook mapping with pattern transfer (ablation) | TransFIR · 4 TKG benchmarks, Hits@10 | Hits@10 | Improved |
| add Interaction Chain construction (ablation) | TransFIR · 4 TKG benchmarks, Hits@10 | Hits@10 | Improved |
| add frozen textual encoding (ablation) | TransFIR · GDELT | Hits@10 | Mixed |
| add frozen textual encoding (ablation) | TransFIR · ICEWS14, ICEWS18 | Hits@10 | Improved |
| use BERT instead of T5 text encoder (ablation) | TransFIR · ICEWS14 | Hits@10: 0.3057 -> 0.3246 | Improved |
| use BERT instead of Qwen3-Embedding (ablation) | TransFIR · ICEWS14 | Hits@10: 0.2567 -> 0.3246 | Improved |
| use RoBERTa instead of BERT (ablation) | TransFIR · GDELT | Hits@10: 0.2278 -> 0.2289 | No clear effect |
| use any PLM versus strongest baseline (ablation) | TransFIR · ICEWS14 | Hits@10: 0.2273 -> 0.2567 (worst PLM) | Improved |
| add VQ codebook and pattern transfer (TransFIR) vs LogCL | TransFIR · ICEWS14 | Collapse Ratio: 0.0055 -> 0.8677 | Improved |
| use TransFIR instead of strongest baseline | TransFIR · GDELT | MRR: 0.0733 -> 0.1103 | Improved |
| chain length k beyond 30 (ablation) | TransFIR · hyperparameter sweep | accuracy | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- InGram — InGram: Inductive Knowledge Graph Embedding via Relation Graphs (ICML 2023) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Interpreting Temporal Knowledge Graph Reasoning (Student Abstract) (AAAI 2024 · similarity 0.88)
- Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning (NeurIPS 2024 · similarity 0.87)
- TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs (NeurIPS 2024 · similarity 0.87)
- CognTKE: A Cognitive Temporal Knowledge Extrapolation Framework (AAAI 2025 · similarity 0.87)
- TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning (AAAI 2024 · similarity 0.87)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.86)
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.
