Research map / Graph learning / Knowledge and temporal graphs
Rule-Guided Compositional Representation Learning on 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 |
|---|---|---|---|
| integrate Horn rules with paths and triple embeddings | RPJE · FB15K entity prediction | MRR (filtered): 0.794 -> 0.816 | Helped |
| integrate Horn rules with paths and triple embeddings | RPJE · FB15K-237 entity prediction | MRR: 0.363 -> 0.470 | Helped |
| integrate Horn rules with paths and triple embeddings | RPJE · WN18 entity prediction | MRR: 0.943 -> 0.946 | Helped |
| integrate Horn rules with paths and triple embeddings | RPJE · NELL-995 entity prediction | Hits@10 (%): 43.7 -> 50.1 | Helped |
| add paths and length-2 rule composition (ablation) | RPJE · FB15K entity prediction | MRR (filtered): 0.453 -> 0.816 | Helped |
| add paths and length-2 rule composition (ablation) | RPJE · FB15K entity prediction | Hits@10 (filtered): 72.1 -> 90.3 | Helped |
| add length-1 relation association rules (ablation) | RPJE · FB15K entity prediction | MRR (filtered): 0.812 -> 0.816 | Helped |
| add length-1 relation association rules (ablation) | RPJE · FB15K entity prediction | Hits@10 (filtered): 90.0 -> 90.3 | Helped |
| use maximum 2-step paths instead of maximum 3-step paths (ablation) | RPJE · FB15K entity prediction | performance (metric unspecified in text) | Helped |
| weight rules by confidence and filter using a moderate confidence threshold (ablation) | RPJE · FB15K entity prediction | performance (metric unspecified in text) | Helped |
| ignore rule confidence and include lower-confidence rules (ablation) | RPJE-min · FB15K entity prediction | performance (metric unspecified in text) | Hurt |
Closest papers by meaning
- Knowledge Graph Embedding With Iterative Guidance From Soft Rules (AAAI 2018 · similarity 0.90)
- Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning (ICLR 2023 · similarity 0.89)
- BoxE: A Box Embedding Model for Knowledge Base Completion (NeurIPS 2020 · similarity 0.88)
- Improving Soft Unification with Knowledge Graph Embedding Methods (ICML 2025 · similarity 0.87)
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.87)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · 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.