Research map / Graph learning / Knowledge and temporal graphs
Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning With Confidence
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 triple confidence weighting to TransE training | TransE · FB15K-N1 | Hits@10 (Filter): 59.8 -> 61.6 | Helped |
| Add triple confidence weighting to TransE training | TransE · FB15K-N2 | Hits@10 (Filter): 56.3 -> 59.3 | Helped |
| Add triple confidence weighting to TransE training | TransE · FB15K-N3 | Hits@10 (Filter): 51.8 -> 56.6 | Helped |
| Add triple confidence weighting to TransE training | TransE · FB15K-N1 | triple classification accuracy: 81.3 -> 81.7 | Helped |
| Add triple confidence weighting to TransE training | TransE · FB15K-N2 | triple classification accuracy: 79.4 -> 80.2 | Helped |
| Add triple confidence weighting to TransE training | TransE · FB15K-N3 | triple classification accuracy: 76.9 -> 78.3 | Helped |
| Add global path confidence to local triple confidence (ablation) | CKRL (LT) · FB15K-N1, FB15K-N2, and FB15K-N3 | Hits@10 (Filter): 61.8 -> 61.6; 59.5 -> 59.4; 56.9 -> 56.8 | No clear effect |
| Add adaptive path confidence to local and prior path confidence (ablation) | CKRL (LT+PP) · FB15K-N1, FB15K-N2, and FB15K-N3 | Hits@10 (Filter): 61.6 -> 61.6; 59.4 -> 59.3; 56.8 -> 56.6 | No clear effect |
| Add global path confidence to local triple confidence (ablation) | CKRL (LT) · FB15K-N1, FB15K-N2, and FB15K-N3 | triple classification accuracy: 81.8 -> 81.9; 80.2 -> 80.1; 78.3 -> 78.4 | Mixed |
| Add adaptive path confidence to local and prior path confidence (ablation) | CKRL (LT+PP) · FB15K-N1, FB15K-N2, and FB15K-N3 | triple classification accuracy: 81.9 -> 81.7; 80.1 -> 80.2; 78.4 -> 78.3 | Mixed |
| Add global path information to local confidence (ablation) | CKRL (LT) · Knowledge graph noise detection | precision at recall 10% | Helped |
| Add adaptive path confidence to local and prior path confidence (ablation) | CKRL (LT+PP) · Knowledge graph noise detection | precision at recall 10%: 84~94% | Helped |
Closest papers by meaning
- Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning (NeurIPS 2025 · similarity 0.88)
- Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs (ICML 2025 · similarity 0.86)
- Knowledge Graph Error Detection with Contrastive Confidence Adaption (AAAI 2024 · similarity 0.86)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.86)
- MKGL: Mastery of a Three-Word Language (NeurIPS 2024 · similarity 0.85)
- PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning (ICML 2024 · 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.