Research map / Graph learning / Knowledge and temporal graphs
Embedding Uncertain Knowledge Graphs
Xuelu Chen, Muhao Chen, Weijia Shi, Yizhou Sun, Carlo Zaniolo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 PSL reasoning for unseen relation facts (ablation) | UKGE_rect · CN15k | MSE: 9.02 -> 8.61 | Improved |
| add PSL reasoning for unseen relation facts (ablation) | UKGE_rect · NL27k | MSE: 2.67 -> 2.36 | Improved |
| add PSL reasoning for unseen relation facts (ablation) | UKGE_rect · PPI5k | MSE: 0.96 -> 0.95 | Improved |
| add negative sampling (ablation) | UKGE_rect · CN15k | MSE: 23.96 -> 8.61 | Improved |
| add negative sampling (ablation) | UKGE_rect · NL27k | MSE: 24.86 -> 2.36 | Improved |
| add negative sampling (ablation) | UKGE_rect · PPI5k | MSE: 7.46 -> 0.95 | Improved |
| use logistic rather than bounded-rectifier confidence mapping (ablation) | UKGE · CN15k, NL27k, PPI5k | nDCG (linear gain): 0.773 -> 0.789; 0.939 -> 0.955; 0.946 -> 0.970 | Improved |
| use logistic rather than bounded-rectifier confidence mapping (ablation) | UKGE · CN15k, NL27k, PPI5k | MSE: 8.61 -> 9.86; 2.36 -> 3.43; 0.95 -> 0.96 | Hurt |
Closest papers by meaning
- Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning (NeurIPS 2025 · similarity 0.89)
- Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspective (AAAI 2025 · similarity 0.87)
- PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning (ICML 2024 · similarity 0.86)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.86)
- KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding (AAAI 2024 · similarity 0.86)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.86)
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.
