Research map / Label-efficient and robust learning / Knowledge distillation
IterDE: An Iterative Knowledge Distillation Framework for Knowledge Graph Embeddings
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 iterative distillation rather than direct 512-to-32 distillation (ablation) | IterDE with TransE · FB15K-237 | MRR: 0.259 -> 0.266 | Helped |
| Use iterative distillation rather than direct 512-to-32 distillation (ablation) | IterDE with ComplEx · FB15K-237 | MRR: 0.246 -> 0.277 | Helped |
| Use iterative distillation rather than direct 512-to-32 distillation (ablation) | IterDE with SimplE · WN18RR | MRR: 0.344 -> 0.387 | Helped |
| Use iterative distillation rather than direct 512-to-32 distillation (ablation) | IterDE with RotatE · FB15K-237 | MRR: 0.280 -> 0.310 | Helped |
| Add soft-label weighting dynamic adjustment (SWDA) (ablation) | IterDE with TransE · FB15K-237 | MRR: 0.264 -> 0.266 | Helped |
| Add soft-label weighting dynamic adjustment (SWDA) (ablation) | IterDE with ComplEx · FB15K-237 | MRR: 0.264 -> 0.277 | Helped |
| Add soft-label weighting dynamic adjustment (SWDA) (ablation) | IterDE with SimplE · WN18RR | MRR: 0.347 -> 0.387 | Helped |
| Add soft-label weighting dynamic adjustment (SWDA) (ablation) | IterDE with RotatE · WN18RR | MRR: 0.429 -> 0.471 | Helped |
| Use a per-iteration compression ratio of 2 instead of 16 (ablation) | IterDE with ComplEx · FB15K-237 | MRR: 0.246 -> 0.277 | Helped |
| Use a per-iteration compression ratio of 2 instead of 16 (ablation) | IterDE with SimplE · WN18RR | MRR: 0.344 -> 0.387 | Helped |
| Use IterDE rather than DualDE | 32-dimensional TransE · WN18RR | MRR: 0.210 -> 0.218 | Helped |
| Use IterDE rather than DualDE | 32-dimensional RotatE · FB15K-237 | MRR: 0.306 -> 0.310 | Helped |
Closest papers by meaning
- Towards Continual Knowledge Graph Embedding via Incremental Distillation (AAAI 2024 · similarity 0.90)
- Knowledge Graph Embedding With Iterative Guidance From Soft Rules (AAAI 2018 · similarity 0.90)
- KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding (AAAI 2024 · similarity 0.87)
- KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge (NeurIPS 2024 · similarity 0.86)
- Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding (NeurIPS 2024 · similarity 0.86)
- 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 0.86)
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.