Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data

TL;DR

This paper introduces FC-STGNN, a novel graph neural network that fully models spatial-temporal dependencies in multivariate time-series data by connecting sensors across all timestamps based on their temporal distances.

Contribution

The paper proposes a fully-connected spatial-temporal graph construction and convolution method that captures correlations between sensors at different timestamps, addressing limitations of existing GNN approaches.

Findings

Outperforms state-of-the-art methods on multiple datasets

Effectively models complex spatial-temporal dependencies

Demonstrates significant improvement in predictive accuracy

Abstract

Multivariate Time-Series (MTS) data is crucial in various application fields. With its sequential and multi-source (multiple sensors) properties, MTS data inherently exhibits Spatial-Temporal (ST) dependencies, involving temporal correlations between timestamps and spatial correlations between sensors in each timestamp. To effectively leverage this information, Graph Neural Network-based methods (GNNs) have been widely adopted. However, existing approaches separately capture spatial dependency and temporal dependency and fail to capture the correlations between Different sEnsors at Different Timestamps (DEDT). Overlooking such correlations hinders the comprehensive modelling of ST dependencies within MTS data, thus restricting existing GNNs from learning effective representations. To address this limitation, we propose a novel method called Fully-Connected Spatial-Temporal Graph Neural Network (FC-STGNN), including two key components namely FC graph construction and FC graph convolution. For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances, enabling us to fully model the ST dependencies by considering the correlations between DEDT. Further, we devise FC graph convolution with a moving-pooling GNN layer to effectively capture the ST dependencies for learning effective representations. Extensive experiments show the effectiveness of FC-STGNN on multiple MTS datasets compared to SOTA methods. The code is available at https://github.com/Frank-Wang-oss/FCSTGNN.