Research map / Graph learning / Knowledge and temporal graphs
Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs
Jiajun Chen, Huarui He, Feng Wu, Jie Wang
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 graph-structure information to the relation-correlation model | TACT-base · WN18RR v1 | MRR: .990 -> .995 | Improved |
| Add graph-structure information to the relation-correlation model | TACT-base · FB15k-237 v4 | MRR: .593 -> .575 | Hurt |
| Add graph-structure information to the relation-correlation model | TACT-base · NELL-995 v4 | MRR: .304 -> .571 | Improved |
| Add relation aggregation (ablation) | TACT · WN18RR v1 | MRR: .875 -> .995 | Improved |
| Add topology-aware relation correlation modeling (ablation) | TACT · WN18RR v1 | MRR: .953 -> .995 | Improved |
| Add relation aggregation (ablation) | TACT · FB15k-237 v1 | MRR: .118 -> .830 | Improved |
| Add topology-aware relation correlation modeling (ablation) | TACT · FB15k-237 v1 | MRR: .666 -> .830 | Improved |
| Add relation aggregation (ablation) | TACT · NELL-995 v4 | MRR: .071 -> .571 | Improved |
| Add topology-aware relation correlation modeling (ablation) | TACT · NELL-995 v4 | MRR: .508 -> .571 | Improved |
| Rank candidates by relation frequency rather than using the learned model | inductive relation prediction · WN18RR v1 | MRR: 0.995 -> 0.763 | Hurt |
Closest papers by meaning
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.92)
- Anchoring Path for Inductive Relation Prediction in Knowledge Graphs (AAAI 2024 · similarity 0.89)
- S²DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.89)
- Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs (NeurIPS 2025 · similarity 0.87)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.87)
- Towards Foundation Models for Knowledge Graph Reasoning (ICLR 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.
