Research map / Learning theory and algorithms / Prediction and decision losses
Tree! I am no Tree! I am a low dimensional Hyperbolic Embedding
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 TreeRep instead of Neighbor Join | tree metric reconstruction · Celegan | MAP: 0.713 -> 0.473 | Hurt |
| use TreeRep instead of Neighbor Join | tree metric reconstruction · Celegan | average distortion: 0.124 -> 0.197 | Hurt |
| use TreeRep instead of Neighbor Join | tree metric reconstruction · Celegan | time (seconds): 0.28 -> 0.014 | Helped |
| use TreeRep instead of Neighbor Join | tree metric reconstruction · Zeisel | average distortion: 0.144 -> 0.117 | Helped |
| use TreeRep instead of MST | tree metric reconstruction · CBMC | average distortion: 1.09 -> 0.260 | Helped |
| add heuristic edge-weight optimization using sampled rows (ablation) | TreeRep · Celegan | average distortion: 0.173 -> 0138 | Helped |
| add heuristic edge-weight optimization using sampled rows (ablation) | TreeRep · Celegan | MAP: 0.508 -> 0.539 | Helped |
| use full rather than heuristic edge-weight optimization (ablation) | TreeRep · Diseasome | MAP: 0.911 -> 0.890 | Hurt |
| use full rather than heuristic edge-weight optimization (ablation) | TreeRep · Diseasome | average distortion: 0.106 -> 0.092 | Helped |
| use full rather than heuristic edge-weight optimization (ablation) | TreeRep · CS PhD | MAP: 0.984 -> 0.968 | Hurt |
| use full rather than heuristic edge-weight optimization (ablation) | TreeRep · CS PhD | average distortion: 0.119 -> 0.121 | Mixed |
| learn a tree first rather than optimize a direct hyperbolic embedding | hyperbolic representation learning · most unweighted graph datasets | MAP | Helped |
Closest papers by meaning
- Hyperbolic Embeddings of Supervised Models (NeurIPS 2024 · similarity 0.90)
- Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space (ICML 2025 · similarity 0.90)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.89)
- Fast Hyperboloid Decision Tree Algorithms (ICLR 2024 · similarity 0.88)
- Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy (ICLR 2025 · similarity 0.88)
- Bridging Arbitrary and Tree Metrics via Differentiable Gromov Hyperbolicity (NeurIPS 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.