Research map / Probabilistic and scientific modeling / Molecules and proteins
Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
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 |
|---|---|---|---|
| Optimize embeddings in the Lorentz model instead of the Poincaré model | Taxonomy embeddings · WordNet Nouns, 2 dimensions | MR: 90.7 -> 22.8 | Helped |
| Optimize embeddings in the Lorentz model instead of the Poincaré model | Taxonomy embeddings · WordNet Verbs, 2 dimensions | MAP: 36.5 -> 57.9 | Helped |
| Optimize embeddings in the Lorentz model instead of the Poincaré model | Taxonomy embeddings · EuroVoc, 2 dimensions | MAP: 64.3 -> 87.1 | Helped |
| Optimize embeddings in the Lorentz model instead of the Poincaré model | Taxonomy embeddings · ACM, 2 dimensions | MAP: 69.3 -> 82.9 | Helped |
| Optimize embeddings in the Lorentz model instead of the Poincaré model | Taxonomy embeddings · MeSH, 2 dimensions | MAP: 19.5 -> 34.8 | Helped |
| Optimize embeddings in the Lorentz model instead of the Poincaré model | Taxonomy embeddings · MeSH, 5 dimensions | MR: 14.05 -> 14.13 | Hurt |
Closest papers by meaning
- Lorentzian Distance Learning for Hyperbolic Representations (ICML 2019 · similarity 0.91)
- Representation Tradeoffs for Hyperbolic Embeddings (ICML 2018 · similarity 0.90)
- Hyperbolic Embeddings of Supervised Models (NeurIPS 2024 · similarity 0.89)
- Poincaré Embeddings for Learning Hierarchical Representations (NeurIPS 2017 · similarity 0.89)
- HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts (NeurIPS 2025 · similarity 0.87)
- Learning Structured Representations with Hyperbolic Embeddings (NeurIPS 2024 · 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.