Research map / Graph learning / Knowledge and temporal graphs
Communicative Message Passing for Inductive Relation 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 |
|---|---|---|---|
| use CoMPILE's node-edge communicative message passing instead of GraIL's R-GCN with edge attention | inductive relation reasoning · Original WN18RR, FB15k-237, and NELL-995 inductive splits | AUC-PR: WN18RR-v1: 94.32 -> 98.23; NELL-995-v1: 86.05 -> 80.16 | Mixed |
| add directed enclosing subgraphs instead of undirected enclosing subgraphs (ablation) | CoMPILE · FB15k-237 and NELL-995 extracted inductive datasets | AUC-PR: FB15k-237-v1: 77.80 -> 78.06; NELL-995-v1: 63.25 -> 68.13 | Helped |
| add enhanced edge attention using the full target triplet (ablation) | CoMPILE · FB15k-237-v1 | AUC-PR: 75.79 -> 78.06 | Helped |
| replace GraIL-style edge attention with enhanced edge attention (ablation) | CoMPILE · FB15k-237-v2 | AUC-PR: 78.53 -> 81.09 | Helped |
| add edge embedding updating (ablation) | CoMPILE · FB15k-237-v1 and v2 | AUC-PR: 76.69 -> 78.06; 79.64 -> 81.09 | Helped |
| include relation information in edge embedding updating (ablation) | CoMPILE · FB15k-237-v1 and v2 | AUC-PR: 77.74 -> 78.06; 79.25 -> 81.09 | Helped |
| score reversed head-tail triplets using CoMPILE | CoMPILE · Asymmetric relations in FB15k-237-v1 | AUC: 67.11 -> 67.11 | No clear effect |
Closest papers by meaning
- MINES: Message Intercommunication for Inductive Relation Reasoning over Neighbor-Enhanced Subgraphs (AAAI 2024 · similarity 0.91)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.90)
- S²DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.89)
- Anchoring Path for Inductive Relation Prediction in Knowledge Graphs (AAAI 2024 · similarity 0.88)
- Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion (ICML 2025 · similarity 0.88)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.88)
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.