Research map / Graph learning / Knowledge and temporal graphs
Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings
Jie Wang, Zhanqiu Zhang, Zhihao Shi, Jianyu Cai, Shuiwang Ji, Feng Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 regularizer | CP · WN18RR | MRR: .438 -> .478 | Improved |
| add DURA regularizer | RESCAL · WN18RR | MRR: .455 -> .498 | Improved |
| add DURA regularizer | ComplEx · FB15k-237 | MRR: .346 -> .371 | Improved |
| add DURA regularizer | RESCAL · WN18RR | H@10: .493 -> .577 | Improved |
| replace N3 regularizer with DURA | CP · FB15k-237 | MRR: .354 -> .367 | Improved |
| replace N3 regularizer with DURA | ComplEx · FB15k-237 | MRR: .366 -> .371 | Improved |
| replace squared Frobenius regularizer with DURA | RESCAL · WN18RR | MRR: .397 -> .498 | Improved |
| add squared Frobenius regularizer | RESCAL · WN18RR | MRR: .455 -> .397 | Hurt |
| add DURA1 regularizer | TComplEx · ICEWS14 | MRR: .60 -> .64 | Improved |
| add DURA1 regularizer | TRESCAL · ICEWS05-15 | MRR: .65 -> .67 | Improved |
| add DURA2 regularizer | TComplEx · YAGO15k | MRR: .35 -> .35 | No clear effect |
| add second half of regularizer (DURA-II) to DURA-I to form full DURA (ablation) | CP · WN18RR | MRR: .463 -> .478 | Improved |
Closest papers by meaning
- What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings (ICML 2023 · similarity 0.88)
- Entity Alignment between Knowledge Graphs Using Attribute Embeddings (AAAI 2019 · similarity 0.88)
- TorusE: Knowledge Graph Embedding on a Lie Group (AAAI 2018 · similarity 0.88)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.86)
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation (Abstract Reprint) (AAAI 2024 · similarity 0.86)
- KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge (NeurIPS 2024 · 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.
