Research map / Graph learning / Knowledge and temporal graphs
Relational Graph Neural Network with Hierarchical Attention for Knowledge Graph Completion
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 hierarchical-attention GNN encoder over ConvE decoder (ablation) | ConvE · FB15k-237 | MRR: 0.325 -> 0.522 | Helped |
| add hierarchical-attention GNN encoder over ConvE decoder (ablation) | ConvE · FB15k high-degree entities (T test 1) | MRR: 0.669 -> 0.843 | Helped |
| add hierarchical-attention GNN encoder over ConvE decoder (ablation) | ConvE · WN18 low-degree (T test 3) | MRR: 0.933 -> 0.936 | No clear effect |
| ConvE decoder instead of DistMult or ConvKB (ablation) | RGHAT · KGC benchmarks | MRR | Helped |
| RGHAT vs RotatE | KGC · WN18 | MR: 309 vs 342 | Hurt |
| RGHAT vs Nathani's GAT | KGC · FB15k-237 | MRR: 0.518 -> 0.522 | No clear effect |
Closest papers by meaning
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.88)
- Mixed Geometry Message and Trainable Convolutional Attention Network for Knowledge Graph Completion (AAAI 2024 · similarity 0.88)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.87)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.87)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.87)
- KGCRR: An Effective Metric-Driven Knowledge Graph Completion Framework by Designing a Novel Upper Bound Function with Adaptive Approximation to Reciprocal Rank (AAAI 2025 · similarity 0.85)
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.