AI Paper Atlas

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

ICML 2023 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 1 citations (OpenAlex)

Read the paper

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 changedWhereMeasuredEffect
Use HDD instead of the strongest baselineUnsupervised hierarchical metric learning · Zoo, Iris, Glass, ImaSegclassification accuracy: 0.861 -> 0.898; 0.895 -> 0.883; 0.610 -> 0.654; 0.679 -> 0.701Mixed
Use multi-scale hyperbolic diffusion distance instead of competing embedding methodsHierarchical graph embedding benchmarks · Five benchmark graphsMAPImproved
Use HDD instead of TR, hMDS, or PTHierarchical graph embedding benchmarks · Five benchmark graphsaverage distortionHurt
Use HDD instead of competing methodsSingle-cell hierarchical distance recovery · Zeisel and CBMCMAPImproved
Use HDD instead of competing methodsSingle-cell hierarchical distance recovery · Zeisel and CBMCaverage distortionImproved
Use HDD instead of competing methodsNearest-centroid classification using recovered distances · Zeisel and CBMCclassification accuracyImproved
Use HDD instead of PE, PT, or HHCHierarchical graph embedding and scRNA-seq experiments · Graph benchmarks and scRNA-seq datasetsrun timeImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy