Research map / Learning theory and algorithms / Matrix and tensor methods
Canonical Tensor Decomposition for Knowledge Base 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 |
|---|---|---|---|
| Add reciprocal predicates to CP-N3 (ablation) | CP-N3 · WN18 | MRR: 0.20 -> 0.95 | Helped |
| Add reciprocal predicates to CP-N3 (ablation) | CP-N3 · WN18RR | MRR: 0.12 -> 0.47 | Helped |
| Add reciprocal predicates to CP-N3 (ablation) | CP-N3 · FB15K | MRR: 0.46 -> 0.86 | Helped |
| Add reciprocal predicates to CP-N3 (ablation) | CP-N3 · FB15K-237 | MRR: 0.33 -> 0.36 | Helped |
| Add reciprocal predicates to CP-N3 (ablation) | CP-N3 · YAGO3-10 | MRR: 0.38 -> 0.57 | Helped |
| Add reciprocal predicates to ComplEx-N3 (ablation) | ComplEx-N3 · WN18 | MRR: 0.95 -> 0.95 | No clear effect |
| Add reciprocal predicates to ComplEx-N3 (ablation) | ComplEx-N3 · WN18RR | MRR: 0.47 -> 0.48 | Helped |
| Add reciprocal predicates to ComplEx-N3 (ablation) | ComplEx-N3 · FB15K | MRR: 0.80 -> 0.86 | Helped |
| Add reciprocal predicates to ComplEx-N3 (ablation) | ComplEx-N3 · FB15K-237 | MRR: 0.35 -> 0.37 | Helped |
| Add reciprocal predicates to ComplEx-N3 (ablation) | ComplEx-N3 · YAGO3-10 | MRR: 0.49 -> 0.58 | Helped |
| Use N3 rather than Frobenius regularization (ablation) | CP with reciprocal predicates · FB15K-237 | MRR: 0.34 -> 0.36 | Helped |
| Use N3 rather than Frobenius regularization (ablation) | CP with reciprocal predicates · YAGO3-10 | MRR: 0.54 -> 0.57 | Helped |
Closest papers by meaning
- Knowledge Graph Completion by Intermediate Variables Regularization (NeurIPS 2024 · similarity 0.90)
- SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph Completion (AAAI 2025 · similarity 0.89)
- Tensor Decomposition Meets Knowledge Compilation: A Study Comparing Tensor Trains with OBDDs (AAAI 2025 · similarity 0.87)
- Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation (NeurIPS 2024 · similarity 0.86)
- tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs) (ICML 2024 · similarity 0.84)
- Modeling Knowledge Graphs with Composite Reasoning (AAAI 2024 · similarity 0.84)
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.