Research map / Graph learning / Knowledge and temporal graphs
TorusE: Knowledge Graph Embedding on a Lie Group
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 |
|---|---|---|---|
| Replace TransE's real-vector embedding space and entity normalization with torus embeddings | TransE · WN18 | HITS@1: 0.040 -> 0.943 | Helped |
| Replace TransE's real-vector embedding space and entity normalization with torus embeddings | TransE · FB15K | HITS@1: 0.247 -> 0.674 | Helped |
| Use torus embeddings instead of real-vector embeddings with normalization | TransE · WN18 | filtered MRR: 0.397 -> 0.947 | Helped |
| Use torus embeddings instead of real-vector embeddings with normalization | TransE · FB15K | filtered MRR: 0.414 -> 0.733 | Helped |
| Use torus embeddings instead of real-vector embeddings with normalization | TransE · WN18 | HITS@10: 0.923 -> 0.954 | Helped |
| Use torus embeddings instead of real-vector embeddings with normalization | TransE · FB15K | HITS@10: 0.688 -> 0.832 | Helped |
| Replace ComplEx with the less-redundant TorusE formulation | ComplEx · WN18 | HITS@1: 0.936 -> 0.943 | Helped |
| Replace ComplEx with the less-redundant TorusE formulation | ComplEx · FB15K | HITS@1: 0.599 -> 0.674 | Helped |
| Replace ComplEx with TorusE | ComplEx · FB15K | HITS@10: 0.840 -> 0.832 | Hurt |
| Replace TransE with TorusE, eliminating the per-epoch entity-normalization calculation | TransE · WN18, dimension 10,000 | training time (seconds per epoch): 55.6 seconds -> 4.0 seconds | Helped |
| Replace TransE with TorusE, eliminating the per-epoch entity-normalization calculation | TransE · FB15K, dimension 10,000 | training time (seconds per epoch): 29.4 seconds -> 16.8 seconds | Helped |
Closest papers by meaning
- Locally Adaptive Translation for Knowledge Graph Embedding (AAAI 2016 · similarity 0.91)
- TransGate: Knowledge Graph Embedding with Shared Gate Structure (AAAI 2019 · similarity 0.90)
- Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding (NeurIPS 2024 · similarity 0.89)
- Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization (ICML 2024 · similarity 0.88)
- KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding (AAAI 2024 · similarity 0.88)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.87)
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.