Spectrally-Regularized Graph Network with Disruption-Aware Training for Out-of-Distribution Robust Traffic Forecasting
TL;DR
SRGNet is proposed, a spectrally-regularized graph network combining three targeted innovations: spectral normalization on all weight matrices to bound the Lipschitz constant, disruption-aware training augmentation synthesizing incident-like flow drops, and stochastic depth creating an implicit ensemble.
Abstract
Spatio-temporal graph neural networks achieve strong traffic forecasting accuracy, yet their robustness under out-of-distribution (OOD) conditions, such as traffic incidents, remains poorly understood. We propose SRGNet, a spectrally-regularized graph network combining three targeted innovations: (1) spectral normalization on all weight matrices to bound the Lipschitz constant; (2) disruption-aware training augmentation synthesizing incident-like flow drops; and (3) stochastic depth creating an implicit ensemble. We evaluate on PEMS-BAY using an impact-verified OOD protocol with 996 real incidents ( 30% flow reduction). SRGNet achieves the lowest OOD degradation (+116.0%) among competitive models, the best local OOD RMSE (0.987) at the most-impacted sensors, and a standard RMSE of 0.3123, demonstrating the best accuracy–robustness tradeoff.