Temporal Graph MLP Mixer for Spatio-Temporal Forecasting

TL;DR

The paper introduces T-GMM, a novel spatiotemporal forecasting model that effectively handles missing data by combining node-level and patch-level processing with a 3D MLP-Mixer, demonstrating strong performance on multiple datasets.

Contribution

The paper presents T-GMM, a new architecture that integrates graph-based and MLP-Mixer components to improve robustness in spatiotemporal forecasting with missing data.

Findings

Effective in forecasting with missing data

Captures long-range dependencies well

Shows strong learning capabilities

Abstract

Spatiotemporal forecasting is critical in applications such as traffic prediction, climate modeling, and environmental monitoring. However, the prevalence of missing data in real-world sensor networks significantly complicates this task. In this paper, we introduce the Temporal Graph MLP-Mixer (T-GMM), a novel architecture designed to address these challenges. The model combines node-level processing with patch-level subgraph encoding to capture localized spatial dependencies while leveraging a three-dimensional MLP-Mixer to handle temporal, spatial, and feature-based dependencies. Experiments on the AQI, ENGRAD, PV-US and METR-LA datasets demonstrate the model's ability to effectively forecast even in the presence of significant missing data. While not surpassing state-of-the-art models in all scenarios, the T-GMM exhibits strong learning capabilities, particularly in capturing long-range dependencies. These results highlight its potential for robust, scalable spatiotemporal forecasting.