AI Paper Atlas

Research map / Graph learning / GNN architectures

How Can State Space Models Enhance Machine Learning on Graphs?

Yinan Huang, Siqi Miao, Pan Li

TPAMI 2026 · Graph learning › GNN architectures · approach: GNN generalization theory · 18 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
replace full-attention graph transformer module with GSSC (ablation)GraphGPS · CIFAR10accuracy: 72.298 -> 77.642Improved
replace attention with GSSC (ablation)GraphGPS · PascalVOC-SPF1: 0.3748 -> 0.4561Improved
replace attention with GSSC (ablation)GraphGPS · Peptides-funcAP: 0.6535 -> 0.7081Improved
replace attention with GSSC (ablation)GraphGPS · ZINC-12kMAE: 0.070 -> 0.064Improved
replace attention with GSSC (ablation)GraphGPS · ogbg-molhivAUROC: 78.80 -> 80.35Improved
add GSSC to an MPNN to predict 5-cyclesGIN · Cycle counting 5-cyclenormalized MAE: 0.2088 -> 0.0113Improved
add GSSC compared with ID-GNN on 5-cyclesID-GIN · Cycle counting 5-cyclenormalized MAE: 0.0490 -> 0.0113Improved
GSSC versus I2-GNN on 5-cycle countingI2-GNN · Cycle counting 5-cyclenormalized MAE: 0.0028 -> 0.0113Hurt
GSSC versus I2-GNN on 3-cycle countingI2-GNN · Cycle counting 3-cyclenormalized MAE: 0.0003 -> 0.0002Improved
GSSC versus Grit on CLUSTERGrit · CLUSTERaccuracy: 80.026 -> 79.156Hurt
GSSC versus GRED on Peptides-funcGRED · Peptides-funcAP: 0.7133 -> 0.7081Hurt
GSSC versus Graph-Mamba-I on CIFAR10Graph-Mamba-I · CIFAR10accuracy: 73.700 -> 77.642Improved

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