AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

SeedGNN: Graph Neural Network for Supervised Seeded Graph Matching

Liren Yu, Jiaming Xu, Xiaojun Lin

ICML 2023 · Graph learning › Graph algorithms and clustering · approach: Deep learning for graph matching · 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
Pair-wise SeedGNN with seeds encoded as 0/1 indicators vs node-based semi-supervised / supervised GNNsseeded graph matching · SHREC'16Accuracy (%): 43.1 vs 37.9 (best baseline NGM)Improved
Hungarian-based cleaning (masking) of similarity matrix before passing seeds to next layer (ablation)MLP+SeedGNN pipeline on Willow Object · Willow ObjectMean accuracy (%): 97.5 vs 85.6Improved
SeedGNN refinement of seedless DGMC outputDGMC on Willow Object · Willow ObjectMean accuracy (%): 98.9 vs 93.7Improved
SeedGNN refinement of MLP similarities (no cleaning)MLP on Willow Object · Willow ObjectMean accuracy (%): 85.6 vs 71.1Improved
Pair-wise architecture normalization removed (SeedGNN vs NGM-like normalization by degrees)correlated Erdos-Renyi test graphs with larger n and dense p=0.2 · correlated Erdos-Renyi (n=500, p=0.2)matching accuracyImproved
Percolation module removed (SeedGNN-w) (ablation)SeedGNN · correlated Erdos-Renyi (n=500, p=0.04)matching accuracyImproved
Convolution at larger hops removed (SeedGNN-x, 1-hop only) (ablation)SeedGNN · correlated Erdos-Renyi (n=500, p=0.04)matching accuracyImproved
Hungarian cleaning removed from percolation (soft similarity only, SeedGNN-p) (ablation)SeedGNN · correlated Erdos-Renyi (n=500, p=0.04)matching accuracyImproved
Using only hard Hungarian matches as new seeds without confidence (SeedGNN-h) (ablation)SeedGNN · correlated Erdos-Renyi (n=500, p=0.04)matching accuracyImproved
Trained with NGM normalization vs not on SHREC'16 (NGM trained on SHREC'16 test-like degrees)NGM on SHREC'16 · SHREC'16matching accuracy: NGM 37.9 vs SeedGNN 43.1No clear effect
Semi-supervised GNNs (DeepLink, CrossMNA, MGCN) vs supervised SeedGNN on SHREC'16 with few seedssemi-supervised GNNs · SHREC'16Accuracy (%): 3.3-4.2 vs 43.1Hurt

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