Research map / Graph learning / Knowledge and temporal graphs
Type-augmented Relation Prediction in Knowledge Graphs
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 the hierarchy-based type prior to RotatE at decision level | RotatE / TaRP-R · FB15K | Hits@1: 80.20 -> 92.91 | Helped |
| Add the hierarchy-based type prior to RotatE at decision level | RotatE / TaRP-R · YAGO26K-906 | Hits@1: 92.84 -> 92.84 | No clear effect |
| Add the hierarchy-based type prior to RotatE at decision level | RotatE / TaRP-R · DB111K-174 | Hits@1: 65.90 -> 76.50 | Helped |
| Add type information to RotatE at decision level | RotatE / TaRP-R · FB15K-237 | MR: 1.88 -> 1.19 | Helped |
| Use hierarchy-based weights instead of uniform type weights (ablation) | Prior model · FB15K | Hits@1: 4.95 -> 64.10 | Helped |
| Use hierarchy-based weights instead of uniform type weights (ablation) | Prior model · YAGO26K-906 | Hits@1: 71.85 -> 79.60 | Helped |
| Use hierarchy-based weights instead of uniform type weights (ablation) | Prior model · DB111K-174 | Hits@1: 19.62 -> 55.00 | Helped |
| Add tail-entity types alongside head-entity types (ablation) | Prior model · FB15K | Hits@1: 8.00 -> 64.10 | Helped |
| Add head-entity types alongside tail-entity types (ablation) | Prior model · YAGO26K-906 | Hits@1: 65.20 -> 71.40 | Helped |
| Train RotatE using type triples on FB15K | RotatE(w/Type) · FB15K | Hits@1: 80.20 -> 73.63 | Hurt |
| Use transferred type information from YAGO26K-906 | TaRP-R on FB15K · FB15K | Hits@1: 82.47 -> 85.77 | Helped |
| Use the union of within-dataset and transferred type information | TaRP-R on DB111K-174 · DB111K-174 | Hits@1: 79.42 -> 86.57 | Helped |
Closest papers by meaning
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.88)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.87)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.85)
- Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction (NeurIPS 2024 · similarity 0.85)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.85)
- Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs (ICML 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.