Automated Spatio-Temporal Graph Contrastive Learning

Abstract

Among various region embedding methods, graph-based region relation learning models stand out, owing to their strong structure representation ability for encoding spatial correlations with graph neural networks. Despite their effectiveness, several key challenges have not been well addressed in existing methods: i) Data noise and missing are ubiquitous in many spatio-temporal scenarios due to a variety of factors. ii) Input spatio-temporal data (e.g., mobility traces) usually exhibits distribution heterogeneity across space and time. In such cases, current methods are vulnerable to the quality of the generated region graphs, which may lead to suboptimal performance. In this paper, we tackle the above challenges by exploring the Automated Spatio-Temporal graph contrastive learning paradigm (AutoST) over the heterogeneous region graph generated from multi-view data sources. Our AutoST framework is built upon a heterogeneous graph neural architecture to capture the multi-view region dependencies with respect to POI semantics, mobility flow patterns and geographical positions. To improve the robustness of our GNN encoder against data noise and distribution issues, we design an automated spatio-temporal augmentation scheme with a parameterized contrastive view generator. AutoST can adapt to the spatio-temporal heterogeneous graph with multiview semantics well preserved. Extensive experiments for three downstream spatio-temporal mining tasks on several real-world datasets demonstrate the significant performance gain achieved by our AutoST over a variety of baselines. The code is publicly available at https://github.com/HKUDS/AutoST.

Spatio-Temporal Meta Contrastive Learning

“…Spatio-temporal prediction, with its focus on analyzing and extracting insights from large and diverse spatio-temporal datasets, has become increasingly vital in numerous real-world applications. Examples include traffic prediction [25,54,56], crime prediction [15,47], and epidemic forecasting [21,42]. By leveraging these predictive techniques, various challenging problems such as transportation management and public safety risk assessment can be addressed and alleviated effectively.…”

Spatial-Temporal Graph Contrastive Learning for Urban Traffic Flow Forecasting

“…At present, the issue of data noise and incompleteness have attracted much attention in traffic forecasting study. Actually, urban networks are inevitably exposed to various incidents such as traffic accidents, sensor malfunctions and large-scale power outrages, leading to the presence of missing data [19], [20]. In this context, methods integrating self-supervised learning, especially contrastive learning, are gradually rising to prominence.…”