Research map / Graph learning / Knowledge and temporal graphs
Knowledge Graph Embedding With Iterative Guidance From Soft Rules
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 iterative soft-rule guidance to ComplEx | ComplEx on FB15K · FB15K test | MRR: 0.690 -> 0.768; 11% | Helped |
| add iterative soft-rule guidance to ComplEx | ComplEx on FB15K · FB15K test | HITS@1: 0.598 -> 0.703; 18% | Helped |
| add iterative soft-rule guidance to ComplEx | ComplEx on YAGO37 · YAGO37 test | MRR: 0.417 -> 0.431; 3% | Helped |
| add iterative soft-rule guidance to ComplEx | ComplEx on YAGO37 · YAGO37 test | HITS@1: 0.320 -> 0.340; 6% | Helped |
| replace one-time rule injection with iterative rule guidance | KG embedding on FB15K and YAGO37 · FB15K and YAGO37 test | MRR | Helped |
| use automatically extracted soft rules, including moderate-confidence rules | RUGE on FB15K · FB15K test | MRR | Helped |
| set the minimum rule confidence threshold above 0.8 (ablation) | RUGE on FB15K · FB15K test | MRR | Hurt |
| set the minimum rule confidence threshold below 0.8 (ablation) | RUGE on FB15K · FB15K test | MRR | Hurt |
| set the minimum rule confidence threshold to 0.8 (ablation) | RUGE on FB15K · FB15K test | MRR | Helped |
Closest papers by meaning
- Rule-Guided Compositional Representation Learning on Knowledge Graphs (AAAI 2020 · similarity 0.90)
- IterDE: An Iterative Knowledge Distillation Framework for Knowledge Graph Embeddings (AAAI 2023 · similarity 0.90)
- Learning Triple Embeddings from Knowledge Graphs (AAAI 2020 · 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 0.88)
- Towards Continual Knowledge Graph Embedding via Incremental Distillation (AAAI 2024 · 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.