EasyST: A Simple Framework for Spatio-Temporal Prediction

TL;DR

EasyST introduces a lightweight, robust framework for spatio-temporal prediction that distills knowledge from complex GNNs into simple MLPs, improving efficiency and accuracy in urban computing tasks.

Contribution

The paper presents a novel simple framework, EasyST, which effectively distills complex GNN models into lightweight MLPs with enhanced generalization for large-scale urban spatio-temporal data.

Findings

EasyST outperforms state-of-the-art methods in accuracy.

EasyST demonstrates superior efficiency in training and deployment.

The framework effectively handles distribution shifts in large-scale data.

Abstract

Spatio-temporal prediction is a crucial research area in data-driven urban computing, with implications for transportation, public safety, and environmental monitoring. However, scalability and generalization challenges remain significant obstacles. Advanced models often rely on Graph Neural Networks to encode spatial and temporal correlations, but struggle with the increased complexity of large-scale datasets. The recursive GNN-based message passing schemes used in these models hinder their training and deployment in real-life urban sensing scenarios. Moreover, long-spanning large-scale spatio-temporal data introduce distribution shifts, necessitating improved generalization performance. To address these challenges, we propose a simple framework for spatio-temporal prediction - EasyST paradigm. It learns lightweight and robust Multi-Layer Perceptrons (MLPs) by effectively distilling knowledge from complex spatio-temporal GNNs. We ensure robust knowledge distillation by integrating the spatio-temporal information bottleneck with teacher-bounded regression loss, filtering out task-irrelevant noise and avoiding erroneous guidance. We further enhance the generalization ability of the student model by incorporating spatial and temporal prompts to provide downstream task contexts. Evaluation on three spatio-temporal datasets for urban computing tasks demonstrates that EasyST surpasses state-of-the-art approaches in terms of efficiency and accuracy. The implementation code is available at: https://github.com/HKUDS/EasyST.