Research map / Image generation / Fast diffusion sampling
Diffusion Scattering Transforms on Graphs
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 diffusion scattering instead of linear graph-signal or GFT features | Linear SVM for authorship attribution · Jane Austen authorship attribution | classification error stability as training graph changes | Helped |
| Use diffusion scattering instead of linear graph-signal or GFT features | Linear SVM for source localization · Facebook source localization | classification error variation under edge perturbations | Helped |
| Increase diffusion scattering depth (ablation) | Diffusion scattering · Graph signal classification | classification accuracy | Helped |
| Increase diffusion scattering depth (ablation) | Diffusion scattering · Small-world graph stability experiment | representation difference | Hurt |
| Increase the spectral-gap parameter β toward one | Diffusion scattering · Small-world graph stability experiment | representation difference | Hurt |
Closest papers by meaning
- Unsupervised Parameter-free Simplicial Representation Learning with Scattering Transforms (ICML 2024 · similarity 0.85)
- Hyperbolic Geometric Latent Diffusion Model for Graph Generation (ICML 2024 · similarity 0.85)
- On Inductive Biases That Enable Generalization in Diffusion Transformers (NeurIPS 2025 · similarity 0.84)
- Generalization in diffusion models arises from geometry-adaptive harmonic representations (ICLR 2024 · similarity 0.84)
- Diffusing Differentiable Representations (NeurIPS 2024 · similarity 0.84)
- SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning (ICML 2025 · similarity 0.84)
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.