Research map / Graph learning / Knowledge and temporal graphs
Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction
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 |
|---|---|---|---|
| Add GRL to DistMult | DistMult · YAGO3-10 | MRR: 34.0 -> 41.2 | Helped |
| Add GRL to ConvE | ConvE · FB15K-237 | MRR: 31.6 -> 32.6 | Helped |
| Add GRL to DistMult | DistMult · NELL-995 | MRR: 48.5 -> 54.3 | Helped |
| Add GRL to ConvE | ConvE · Kinship | MRR: 83.3 -> 83.4 | No clear effect |
| Add GRL to DistMult | DistMult · WN18 | MRR: 82.2 -> 86.1 | Helped |
| Add GRL to ConvE | ConvE · NELL-ONE | MRR: 17.0 -> 25.6 | Helped |
| Add GRL to DistMult | DistMult · NELL-ONE | MRR: 10.2 -> 14.4 | Helped |
| Use only the joint vector instead of adaptive fusion (ablation) | ConvE+GRL · YAGO3-10 | MRR: 55.4 -> 52.6 | Hurt |
| Use only the joint vector instead of adaptive fusion (ablation) | ConvE+GRL · NELL-ONE | MRR: 25.6 -> 23.3 | Hurt |
| Use equal-weight fusion (pf=0.5) instead of adaptive fusion (ablation) | ConvE+GRL · YAGO3-10 | MRR: 55.4 -> 53.9 | Hurt |
| Use equal-weight fusion (pf=0.5) instead of adaptive fusion (ablation) | ConvE+GRL · NELL-ONE | MRR: 25.6 -> 24.7 | Hurt |
| Use only the relational knowledge vector instead of adaptive fusion (ablation) | ConvE+GRL · YAGO3-10 | MRR: 55.4 -> 52.2 | Hurt |
Closest papers by meaning
- HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs (ICLR 2026 · similarity 0.88)
- Inductive Relation Prediction by Subgraph Reasoning (ICML 2020 · similarity 0.87)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.85)
- Learning Concept Prerequisite Relation via Global Knowledge Relation Optimization (AAAI 2025 · similarity 0.85)
- Anchoring Path for Inductive Relation Prediction in Knowledge Graphs (AAAI 2024 · similarity 0.85)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.84)
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.