AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Stochastic Iterative Graph Matching

Linfeng Liu, Michael C Hughes, Soha Hassoun, Liping Liu

ICML 2021 · Graph learning › Graph algorithms and clustering · approach: Deep learning for graph matching · 1 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 SIGMA instead of S-GWLnoisy BA and PPI graph matching · BA(500), BA(1000), BA(2000), and PPI with 5% noisenode correctness (%): 32.0±1.5 -> 93.8±0.3 (BA(500)); 22.9±0.3 -> 97.3±0.2 (BA(1000)); 16.2±0.4 -> 99.0±0.1 (BA(2000)); 81.1 -> 84.7±0.4 (PPI)Improved
Add iterative refinement (T=4) rather than T=0 (ablation)SIGMA · PPI, 5% noisenode correctness (%): 83.1±0.3 -> 84.7±0.4Improved
Add iterative refinement (T=4) rather than T=0 (ablation)SIGMA · BA(500), BA(1000), and BA(2000), 5% noisenode correctness (%): 93.5±0.1 -> 93.8±0.3; 97.2±0.1 -> 97.3±0.2; 98.9±0.1 -> 99.0±0.1No clear effect
Add the stochastic framework (ablation)SIGMA · Noisy BA and PPI graph matchingnode correctness (%): 93.6±0.1 -> 93.8±0.3 (BA(500)); 97.1±0.2 -> 97.3±0.2 (BA(1000)); 98.9±0.1 -> 99.0±0.1 (BA(2000)); 84.1±0.4 -> 84.7±0.4 (Mixed
Add dummy nodes (ablation)SIGMA · Noisy BA and PPI graph matchingnode correctness (%): 50.3±4.1 -> 93.8±0.3 (BA(500)); 75.0±5.9 -> 97.3±0.2 (BA(1000)); 80.4±3.1 -> 99.0±0.1 (BA(2000)); 83.2±0.2 -> 84.7±0.4 (Improved
Use SIGMA instead of DGMCRDM pattern matching · RDM pattern matchingnode correctness (%): 66.9±0.9 -> 78.3±0.8Improved
Add iterative refinement rather than T=0 (ablation)SIGMA · RDM pattern matchingnode correctness (%): 76.4±0.8 -> 78.3±0.8Improved
Add the stochastic framework (ablation)SIGMA · RDM pattern matchingnode correctness (%): 76.0±0.8 -> 78.3±0.8Improved
Add dummy nodes (ablation)SIGMA · RDM pattern matchingnode correctness (%): 63.6±0.9 -> 78.3±0.8Improved
Use the supervised objective in addition to the QAP objective (ablation)SIGMA for RDM pattern matching · RDM pattern matchingnode correctness (%): 66.2±1.0 -> 78.3±0.8Improved
Use SIGMA instead of DGMCPASCAL VOC keypoint matching · PASCAL VOC, Berkeley annotationsHit@1 (%): 73.0 -> 76.2Improved
Add stochastic matching rather than optimizing a single matching (ablation)SIGMA · PASCAL VOC keypoint matchingHit@1 (%): 73.1 -> 76.2Improved

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