Abstract
Spatial-temporal forecasting (STF) plays a pivotal role in urban planning and computing. Spatial-Temporal Graph Neural Networks (STGNNs) excel at modeling spatial-temporal dynamics, thus being robust against noise perturbations. However, they often suffer from relatively poor computational efficiency. Simplifying the architectures can improve efficiency but also weakens robustness with respect to noise interference. In this study, we investigate the problem:can simple neural networks such as Multi-Layer Perceptrons (MLPs) achieve robust spatial-temporal forecasting while remaining efficient?To this end, we first reveal thedual noise effectin spatial-temporal data and propose a theoretically grounded principle termedRobust Spatial-Temporal Information Bottleneck(RSTIB), which holds strong potential for improving model robustness. We then design an implementation namedRSTIB-MLP, together with a new training regime incorporating a knowledge distillation module, to enhance the robustness of MLPs for STF while maintaining their efficiency. Comprehensive experiments demonstrate thatRSTIB-MLPachieves an excellent trade-off between robustness and efficiency, outperforming state-of-the-art STGNNs and MLP-based models. Our code is publicly available at:https://github.com/mchen644/RSTIB.