Research map / Image generation / Fast diffusion sampling
Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning
Ya-Wei Eileen Lin, Ronald R. Coifman, Gal Mishne, Ronen Talmon
AI-extracted. The measured effects below were read by AI from the paper's full text (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 HDD instead of the strongest baseline | Unsupervised hierarchical metric learning · Zoo, Iris, Glass, ImaSeg | classification accuracy: 0.861 -> 0.898; 0.895 -> 0.883; 0.610 -> 0.654; 0.679 -> 0.701 | Mixed |
| Use multi-scale hyperbolic diffusion distance instead of competing embedding methods | Hierarchical graph embedding benchmarks · Five benchmark graphs | MAP | Improved |
| Use HDD instead of TR, hMDS, or PT | Hierarchical graph embedding benchmarks · Five benchmark graphs | average distortion | Hurt |
| Use HDD instead of competing methods | Single-cell hierarchical distance recovery · Zeisel and CBMC | MAP | Improved |
| Use HDD instead of competing methods | Single-cell hierarchical distance recovery · Zeisel and CBMC | average distortion | Improved |
| Use HDD instead of competing methods | Nearest-centroid classification using recovered distances · Zeisel and CBMC | classification accuracy | Improved |
| Use HDD instead of PE, PT, or HHC | Hierarchical graph embedding and scRNA-seq experiments · Graph benchmarks and scRNA-seq datasets | run time | Improved |
Closest papers by meaning
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.89)
- Hyperbolic Embeddings of Supervised Models (NeurIPS 2024 · similarity 0.89)
- Hyperbolic Graph Diffusion Model (AAAI 2024 · similarity 0.88)
- Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction (NeurIPS 2025 · similarity 0.88)
- Hyperbolic Geometric Latent Diffusion Model for Graph Generation (ICML 2024 · similarity 0.88)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · 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.
