Research map / Graph learning / Knowledge and temporal graphs
On Multi-Relational Link Prediction With Bilinear Models
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 |
|---|---|---|---|
| Use a relation-level ensemble of RESCAL, HolE, and TransE instead of the strongest individual model | Bilinear link prediction · WN18 test | HITS@10 (%): 94.5 -> 95.0 | Helped |
| Use a relation-level ensemble of RESCAL, HolE, and TransE instead of the strongest individual model | Bilinear link prediction · WN18 test | MRR (%): 93.8 -> 94.0 | Helped |
| Use a relation-level ensemble of RESCAL, HolE, and TransE instead of the strongest individual model | Bilinear link prediction · FB15K test | HITS@10 (%): 79.5 -> 85.1 | Helped |
| Use a relation-level ensemble of RESCAL, HolE, and TransE instead of the strongest individual model | Bilinear link prediction · FB15K test | MRR (%): 50.2 -> 62.8 | Helped |
| Use a relation-level ensemble of RESCAL, HolE, and TransE instead of the strongest individual model | Bilinear link prediction · FB15K triple classification | Accuracy: 96.2 -> 96.9 | Helped |
| Add RESCAL to a HolE + TransE relation-level ensemble (ablation) | Bilinear link prediction · WN18 test | HITS@10 (%): 94.9 -> 95.0 | Helped |
| Add RESCAL to a HolE + TransE relation-level ensemble (ablation) | Bilinear link prediction · WN18 test | MRR (%): 93.8 -> 94.0 | Helped |
| Add RESCAL to a HolE + TransE relation-level ensemble (ablation) | Bilinear link prediction · FB15K test | HITS@10 (%): 84.6 -> 85.1 | Helped |
| Add RESCAL to a HolE + TransE relation-level ensemble (ablation) | Bilinear link prediction · FB15K test | MRR (%): 61.0 -> 62.8 | Helped |
| Add RESCAL to a HolE + TransE relation-level ensemble (ablation) | Bilinear link prediction · FB15K triple classification | Accuracy: 96.5 -> 96.9 | Helped |
| Use a relation-level ensemble rather than one individual model | Bilinear link prediction · Entity ranking across WN18 and FB15K | MR (mean rank) | Mixed |
Closest papers by meaning
- LowFER: Low-rank Bilinear Pooling for Link Prediction (ICML 2020 · similarity 0.91)
- Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction (AAAI 2023 · similarity 0.88)
- You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings (ICLR 2020 · similarity 0.88)
- Multi-relational Poincaré Graph Embeddings (NeurIPS 2019 · similarity 0.87)
- Relational Pattern Benchmarking on the Knowledge Graph Link Prediction Task (NeurIPS 2021 · similarity 0.87)
- Bridging Theory and Practice in Link Representation with Graph Neural Networks (NeurIPS 2025 · 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.