Research map / Graph learning / Knowledge and temporal graphs
HousE: Knowledge Graph Embedding with Householder Parameterization
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 HousE instead of HousE-r by adding invertible Householder projections (ablation) | HousE-r · WN18 | MRR: .953 -> .954 | Helped |
| Use HousE instead of HousE-r by adding invertible Householder projections (ablation) | HousE-r · FB15k | MRR: .807 -> .811 | Helped |
| Use HousE instead of HousE-r by adding invertible Householder projections (ablation) | HousE-r · WN18RR | MRR: .496 -> .511 | Helped |
| Use HousE instead of HousE-r by adding invertible Householder projections (ablation) | HousE-r · FB15k-237 | MRR: .348 -> .361 | Helped |
| Use HousE instead of HousE-r by adding invertible Householder projections (ablation) | HousE-r · YAGO3-10 | MRR: .565 -> .571 | Helped |
| Replace invertible Householder projections with irreversible TransH projections (ablation) | HousE · WN18RR | MRR: .511 -> .491 | Hurt |
| Replace invertible Householder projections with irreversible TransR projections (ablation) | HousE · WN18RR | MRR: .511 -> .488 | Hurt |
| Replace Householder projections with TransH projections (ablation) | HousE · FB15k-237 | MRR: .361 -> .347 | Hurt |
| Replace Householder projections with TransR projections (ablation) | HousE · FB15k-237 | MRR: .361 -> .349 | Hurt |
| Add translations after Householder rotations (ablation) | HousE-r · WN18RR | MRR: .496 -> .500 | Helped |
| Add translations after Householder rotations (ablation) | HousE-r · FB15k-237 | MRR: .348 -> .351 | Helped |
| Add translations after Householder rotations (ablation) | HousE · WN18RR | MRR: .511 -> .514 | Helped |
Closest papers by meaning
- You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings (ICLR 2020 · similarity 0.90)
- Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization (ICML 2024 · similarity 0.90)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.87)
- KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge (NeurIPS 2024 · similarity 0.87)
- Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding (NeurIPS 2024 · similarity 0.87)
- KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding (AAAI 2024 · 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.