Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning

About

Message-passing neural networks (MPNNs) often suffer from an information bottleneck when capturing long-range dependencies, leading to the oversquashing (OSQ) phenomenon. Alongside spatial connectivity enrichment (e.g., rewiring), recent studies have shown that spectral filtering can yield strong long-range learning outcomes, as spectral operators enable global information mixing that alleviates OSQ. These approaches achieve this either by stabilizing the Jacobian energies in deep propagation or by guaranteeing OSQ mitigation under strong theoretical assumptions. We revisit these conclusions and show that the associated Jacobian sensitivity lower bound is generally difficult to achieve in practice. We then propose S$^3$GNN, which mitigates OSQ without such restrictive assumptions by lightweightly reintroducing omitted components with substantially lower computational complexity, while standard stability constraints on feature transformations remain effective under our new dynamics. Extensive experiments across diverse domains (e.g., long-range benchmarks, KGQA, and mesh-based fluid dynamics) demonstrate that S$^3$GNN achieves up to an order-of-magnitude error reduction with up to 50\% fewer parameters. Our code can be found in https://github.com/EEthanShi/S3-GNN.git.

Dai Shi, Luke Thompson, Linhan Luo, Lequan Lin, Andi Han, Junbin Gao, Jos\'e Miguel Hern\'andez Lobato• 2026

Related benchmarks

TaskDatasetResultRank
Node Classificationogbn-arxiv (test)
Accuracy76.38
497
Knowledge Graph Question AnsweringCWQ--
212
Node ClassificationAmazon-Ratings (test)
Accuracy53.46
155
Node ClassificationMinesweeper (test)
AUROC97.58
134
Graph RegressionPeptides-struct
MAE0.2429
134
Node ClassificationTolokers (test)
AUROC85.89
128
Graph ClassificationPeptides func
AP73.2
110
Diameter predictionGraph Property Prediction (test)
log10(MSE)-0.3301
24
Eccentricity PredictionGraph Property Prediction (test)
log10(MSE)-2.4801
24
SSSP PredictionGraph Property Prediction (test)
log10(MSE)-2.6311
24
Showing 10 of 18 rows

Other info

Follow for update