Research map / Learning theory and algorithms / Matrix and tensor methods
Tensor Decompositions for Temporal 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 timestamp embeddings to ComplEx | ComplEx · ICEWS14 | MRR: 0.47 -> 0.56 | Helped |
| Add timestamp embeddings to ComplEx | ComplEx · ICEWS05-15 | MRR: 0.49 -> 0.58 | Helped |
| Add timestamp embeddings to ComplEx | ComplEx · Yago15k | MRR: 0.35 -> 0.35 | No clear effect |
| Add a non-temporal component | TComplEx · ICEWS05-15 | MRR: 0.58 -> 0.60 | Helped |
| Add a non-temporal component | TComplEx · Wikidata | T-MRR: 0.30 -> 0.32 | Helped |
| Add a non-temporal component | TComplEx · Wikidata | MRR: 0.42 -> 0.44; ComplEx 0.45 | Mixed |
| Increase temporal model rank tenfold | TNTComplEx · ICEWS14 | MRR: 0.56 -> 0.62 | Helped |
| Use Ω³ rather than no regularizer (ablation) | TNTComplEx · ICEWS05-15 | MRR: 0.62 -> 0.65 | Helped |
| Use Δ² rather than no regularizer (ablation) | TNTComplEx · ICEWS05-15 | MRR: 0.62 -> 0.63 | Helped |
| Use Δ³ rather than no regularizer (ablation) | TNTComplEx · ICEWS05-15 | MRR: 0.62 -> 0.63 | Helped |
| Use Δ⁴ rather than no regularizer (ablation) | TNTComplEx · ICEWS05-15 | MRR: 0.62 -> 0.64 | Helped |
| Add temporal smoothness penalty Λ₄ to Ω³ (ablation) | TNTComplEx · ICEWS05-15 | MRR: 0.65 -> 0.67 | Helped |
Closest papers by meaning
- SimplE Embedding for Link Prediction in Knowledge Graphs (NeurIPS 2018 · similarity 0.89)
- Canonical Tensor Decomposition for Knowledge Base Completion (ICML 2018 · similarity 0.88)
- LowFER: Low-rank Bilinear Pooling for Link Prediction (ICML 2020 · similarity 0.86)
- Knowledge Graph Completion by Intermediate Variables Regularization (NeurIPS 2024 · similarity 0.86)
- SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph Completion (AAAI 2025 · similarity 0.86)
- Improving Temporal Link Prediction via Temporal Walk Matrix Projection (NeurIPS 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.