AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Fast Graph Generation via Spectral Diffusion

Tianze Luo, Zhanfeng Mo, Sinno Jialin Pan

TPAMI 2023 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 54 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
diffuse in graph spectrum space instead of whole adjacency matrix (GSDM vs GDSS)Graph diffusion model · Community-smallAvg. MMD: 0.046 -> 0.009Improved
diffuse in graph spectrum space instead of whole spaceGraph diffusion model · GridAvg. MMD: 0.062 -> 0.0007Improved
diffuse in graph spectrum space instead of whole spaceGraph diffusion model · EnzymesAvg. MMD: 0.046 -> 0.037Improved
spectral diffusion instead of GDSS on QM9Graph diffusion model · QM9FCD: 2.900 -> 2.650Improved
spectral diffusion instead of GDSS on ZINC250kGraph diffusion model · ZINC250kValidity w/o correction (%): 97.01 -> 92.70Hurt
spectral diffusion instead of GDSSGraph diffusion model · QM9Generation time (s): 1.06e^3 -> 18.02Improved
spectral diffusion instead of GDSSGraph diffusion model · ZINC250kGeneration time (s): 2.11e^3 -> 45.91Improved
keep only top 30% eigenvalues instead of all (ablation)GSDM · EnzymesAvg. MMD: 0.039 vs 0.038 fullNo clear effect
keep only top 10% eigenvalues instead of all (ablation)GSDM · Community-smallAvg. MMD: 0.009 -> 0.781Hurt
keep only top 60% eigenvalues instead of all (ablation)GSDM · GridAvg. MMD: 0.001 -> 0.001No clear effect
vary number of diffusion steps (GSDM vs GDSS) (ablation)GSDM · Grid and Community-smallperformanceImproved
vary diffusion schedule (VE/VP, six noise schedules) (ablation)GSDM · Ego-small and GridAvg. MMDNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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