ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting

2025-09-27

AI Summary

This work addresses multivariate time-series forecasting under irregular, asynchronous sampling—common in healthcare and finance—where conventional interpolation-based preprocessing introduces distortion. We propose the Adaptive Spatio-Temporal Graph Interaction (ASTGI) framework, which eliminates such preprocessing and instead introduces a learnable spatio-temporal embedding space. ASTGI features a neighborhood-adaptive causal graph construction mechanism and a relative spatio-temporal position–aware message-passing strategy to explicitly model dynamic, asymmetric dependencies among observation points. The architecture comprises four core modules: spatio-temporal point representation, dynamic graph construction, spatio-temporal propagation, and query-point regression, enabling end-to-end training. Extensive experiments on multiple benchmark datasets demonstrate that ASTGI significantly outperforms state-of-the-art methods in prediction accuracy, robustness to sampling irregularity, and cross-domain generalization.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Irregular multivariate time series (IMTS) are prevalent in critical domains like healthcare and finance, where accurate forecasting is vital for proactive decision-making. However, the asynchronous sampling and irregular intervals inherent to IMTS pose two core challenges for existing methods: (1) how to accurately represent the raw information of irregular time series without introducing data distortion, and (2) how to effectively capture the complex dynamic dependencies between observation points. To address these challenges, we propose the Adaptive Spatio-Temporal Graph Interaction (ASTGI) framework. Specifically, the framework first employs a Spatio-Temporal Point Representation module to encode each discrete observation as a point within a learnable spatio-temporal embedding space. Second, a Neighborhood-Adaptive Graph Construction module adaptively builds a causal graph for each point in the embedding space via nearest neighbor search. Subsequently, a Spatio-Temporal Dynamic Propagation module iteratively updates information on these adaptive causal graphs by generating messages and computing interaction weights based on the relative spatio-temporal positions between points. Finally, a Query Point-based Prediction module generates the final forecast by aggregating neighborhood information for a new query point and performing regression. Extensive experiments on multiple benchmark datasets demonstrate that ASTGI outperforms various state-of-the-art methods.

Problem

• Forecasting irregular multivariate time series with asynchronous sampling
• Capturing complex dynamic dependencies between irregular observation points
• Representing raw irregular time series information without data distortion

Innovation

• Encodes observations in learnable spatio-temporal embedding space
• Adaptively builds causal graphs via nearest neighbor search
• Iteratively propagates information on adaptive causal graphs