Research map / Graph learning / Knowledge and temporal graphs
Inductive Relation Prediction by Subgraph Reasoning
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 |
|---|---|---|---|
| reason over extracted enclosing subgraphs rather than the subgraph induced by all k-hop neighbors (ablation) | GraIL · FB15k-237 v3 | AUC-PR: 84.25 -> 91.68 | Helped |
| reason over extracted enclosing subgraphs rather than the subgraph induced by all k-hop neighbors (ablation) | GraIL · NELL-995 v3 | AUC-PR: 85.89 -> 93.34 | Helped |
| use double-radius node labels rather than constant labels (1, 1) (ablation) | GraIL · FB15k-237 v3 | AUC-PR: 82.07 -> 91.68 | Helped |
| use double-radius node labels rather than constant labels (1, 1) (ablation) | GraIL · NELL-995 v3 | AUC-PR: 84.46 -> 93.34 | Helped |
| use attention in the GNN (ablation) | GraIL · FB15k-237 v3 | AUC-PR: 90.27 -> 91.68 | Helped |
| use attention in the GNN (ablation) | GraIL · NELL-995 v3 | AUC-PR: 87.30 -> 93.34 | Helped |
| ensemble GraIL with embedding-based methods | Transductive KGE methods · WN18RR and NELL-995 | AUC-PR: 1.5%; 0.62% | Helped |
| ensemble GraIL with embedding-based methods | Transductive KGE methods · FB15k-237 | AUC-PR | No clear effect |
| concatenate TransE embeddings with GraIL's structural node features (early fusion) | GraIL · WN18RR, FB15k-237, and NELL-995 | AUC-PR: 18.2% | Helped |
| use pooling aggregation or alternative CONCAT/GRU combine functions (ablation) | GraIL · Not specified | performance | No clear effect |
Closest papers by meaning
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.90)
- MINES: Message Intercommunication for Inductive Relation Reasoning over Neighbor-Enhanced Subgraphs (AAAI 2024 · similarity 0.90)
- Towards Foundation Models for Knowledge Graph Reasoning (ICLR 2024 · similarity 0.88)
- Systematic Relational Reasoning With Epistemic Graph Neural Networks (ICLR 2025 · similarity 0.88)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.87)
- Anchoring Path for Inductive Relation Prediction in Knowledge Graphs (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.