Research map / Graph learning / Knowledge and temporal graphs
ProjE: Embedding Projection for Knowledge Graph Completion
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 |
|---|---|---|---|
| Optimize candidate scores collectively with softmax listwise loss instead of sigmoid pointwise loss (ablation) | ProjE · FB15K entity prediction | HITS@10 (Filtered): 86.6 -> 71.2 | Mixed |
| Use instance-level weighting in the listwise loss (ablation) | ProjE_listwise · FB15K entity prediction | HITS@10 (Filtered): 71.2 -> 88.4 | Helped |
| Use instance-level weighting in the listwise loss (ablation) | ProjE_listwise · FB15K entity prediction | Mean Rank (Filtered): 76 -> 34 | Helped |
| Use instance-level weighting in the listwise loss (ablation) | ProjE_listwise · FB15K relationship prediction | HITS@1 (Filtered): 95.7 -> 95.6 | No clear effect |
| Use listwise rather than pointwise candidate scoring (ablation) | ProjE · FB15K relationship prediction | HITS@1 (Filtered): 95.6 -> 95.7 | No clear effect |
| Apply pointwise and listwise ranking losses to TransE (ablation) | TransE · FB15K entity prediction | prediction performance | No clear effect |
| Reduce negative candidate sampling rates to 25% (ablation) | ProjE · FB15K entity prediction | prediction performance | No clear effect |
Closest papers by meaning
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.88)
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.88)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.88)
- SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph Completion (AAAI 2025 · similarity 0.87)
- KGCRR: An Effective Metric-Driven Knowledge Graph Completion Framework by Designing a Novel Upper Bound Function with Adaptive Approximation to Reciprocal Rank (AAAI 2025 · similarity 0.87)
- S²DN: Learning to Denoise Unconvincing Knowledge 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.