AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

PolyGraph Discrepancy: a classifier-based metric for graph generation

Markus Krimmel, Philip Hartout, Karsten Borgwardt, Dexiong Chen

ICLR 2026 · Graph learning › Graph algorithms and clustering · approach: Graph embedding and spectral sparsification · 2 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 PGD instead of MMD metrics for tracking validity across denoising stepsDiGress on Planar-L · Planar-L denoising stepsneg. Pearson corr with validity: 99.29 vs 82.52 (best MMD, GIN RBF)Improved
use PGD instead of MMD for tracking training progressDiGress on SBM-L · SBM-L trainingSpearman corr with training iterations: 77.27 vs 68.18 (Clust. RBF), 23.64 (Orbit RBF)Improved
use PGD instead of MMD on Lobster-L trainingDiGress on Lobster-L · Lobster-L trainingneg. Pearson corr with validity: 86.54 vs 87.05 (Clust. RBF)Mixed
use PGD instead of MMD on perturbation experimentsGraph metrics · Synthetic perturbationsSpearman corr with perturbation magnitudeNo clear effect
use multiple descriptors in PGD to detect edge swappingPGD · Edge-swapping perturbationSpearman corr with perturbation magnitudeImproved
use larger datasets (SBM-L, Planar-L, Lobster-L) with unbiased MMDMMD evaluation · Synthetic graph benchmarksMMD bias and variance: 20-40 test graphs: bias dominatesImproved
use feature concatenation instead of max-reduction over descriptorsPGD · BenchmarkJSD estimate tightnessMixed
pretrain AutoGraph on PubChemAutoGraph · GuacaMolPGD (x100): 27.3 -> 11.5Improved
use PGD-TV instead of PGD-JSPGD · Training progressSpearman corr with trainingHurt

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