AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

AgraSSt: Approximate Graph Stein Statistics for Interpretable Assessment of Implicit Graph Generators

Wenkai Xu, Gesine Reinert

NeurIPS 2022 · Graph learning › Graph algorithms and clustering · approach: Graph embedding and spectral sparsification · 0 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
Use AgraSSt instead of degree-variance statistic Deg to assess NetGANAgraSSt · ERGM-trained generatorsrejection rate: 0.13 -> 0.81Improved
Use AgraSSt instead of Deg to assess GraphRNNAgraSSt · ERGM-trained generatorsrejection rate: 0.02 -> 0.42Improved
Use AgraSSt instead of MDdeg on NetGANAgraSSt · ERGM-trained generatorsrejection rate: 0.61 -> 0.81Improved
Use AgraSSt instead of TV_deg on GraphRNNAgraSSt · ERGM-trained generatorsrejection rate: 0.27 -> 0.42Improved
Run on reliable MC generator: type-I error controlAgraSSt · MC baselinerejection rate: 0.04No clear effect
Estimate q-hat with Edges statistic vs degree-based statistics (Sum_deg, Cum_deg, Bi_deg) (ablation)AgraSSt · Synthetic E2STrejection rate (power)Improved
Use 2-d vector of both vertex degrees instead of sum of degrees (ablation)AgraSSt · Synthetic E2STpowerImproved
Increase re-sampling size B (ablation)AgraSSt · Synthetic E2STpowerImproved
Compare AgraSSt with TV_deg and Deg on synthetic E2STAgraSSt · Synthetic E2STpowerImproved
Use MDdeg and Param instead of AgraSSt on sparse alternativesMDdeg/Param · Synthetic E2STrejection rateHurt
Use AgraSSt instead of Deg on Karate Club GraphRNNAgraSSt · Karate Clubp-value: 0.01 -> 0.00Improved
Use AgraSSt instead of MDdeg on Karate Club NetGANAgraSSt · Karate Clubp-value: 0.59 -> 0.00Improved

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