Research map / Graph learning / Knowledge and temporal graphs
Duality-Induced Regularizer for Tensor Factorization Based 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 |
|---|---|---|---|
| Add DURA to CP | CP · WN18RR | MRR: .438 -> .478 | Helped |
| Add DURA to RESCAL | RESCAL · WN18RR | MRR: .455 -> .498 | Helped |
| Add DURA to ComplEx | ComplEx · WN18RR | MRR: .460 -> .491 | Helped |
| Add DURA to CP | CP · FB15k-237 | MRR: .333 -> .367 | Helped |
| Add DURA to RESCAL | RESCAL · FB15k-237 | MRR: .353 -> .368 | Helped |
| Add DURA to ComplEx | ComplEx · FB15k-237 | MRR: .346 -> .371 | Helped |
| Add DURA to CP | CP · YAGO3-10 | MRR: .567 -> .579 | Helped |
| Add DURA to RESCAL | RESCAL · YAGO3-10 | MRR: .566 -> .579 | Helped |
| Add DURA to ComplEx | ComplEx · YAGO3-10 | MRR: .573 -> .584 | Helped |
| Replace DURA with N3 (ablation) | CP · FB15k-237 | MRR: .367 -> .354 | Hurt |
| Replace DURA with N3 (ablation) | ComplEx · FB15k-237 | MRR: .371 -> .366 | Hurt |
| Replace DURA with squared Frobenius regularization (ablation) | RESCAL · WN18RR | MRR: .498 -> .397 | Hurt |
Closest papers by meaning
- Knowledge Graph Completion by Intermediate Variables Regularization (NeurIPS 2024 · similarity 0.92)
- SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph Completion (AAAI 2025 · similarity 0.89)
- 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 0.85)
- Modeling Knowledge Graphs with Composite Reasoning (AAAI 2024 · similarity 0.85)
- Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion (NeurIPS 2024 · similarity 0.84)
- Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation (NeurIPS 2024 · similarity 0.83)
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.