Graph-Aware Contrasting for Multivariate Time-Series Classification

TL;DR

Multivariate time-series (MTS) classification benefits from representations robust to perturbations across sensors and time. This paper introduces TS-GAC, a graph-aware contrasting framework that enforces spatial consistency via node- and edge-based graph augmentations and graph-level and node-level contrasting, complemented by Multi-Window Temporal Contrasting (MWTC). The method operates on unlabeled data, mapping each sample $X_j \\in \\mathbb{R}^{N\\times L}$ to $h_j \\\\in \\mathbb{R}^d$ through an encoder $\\mathcal{F}$ and evaluating with a linear classifier, achieving state-of-the-art results on ten public MTS datasets, including HAR and ISRUC. The contributions provide a principled approach to incorporating sensor stability and inter-sensor relationships into contrastive learning for MTS, with practical impact on robust, label-efficient time-series classification.

Abstract

Contrastive learning, as a self-supervised learning paradigm, becomes popular for Multivariate Time-Series (MTS) classification. It ensures the consistency across different views of unlabeled samples and then learns effective representations for these samples. Existing contrastive learning methods mainly focus on achieving temporal consistency with temporal augmentation and contrasting techniques, aiming to preserve temporal patterns against perturbations for MTS data. However, they overlook spatial consistency that requires the stability of individual sensors and their correlations. As MTS data typically originate from multiple sensors, ensuring spatial consistency becomes essential for the overall performance of contrastive learning on MTS data. Thus, we propose Graph-Aware Contrasting for spatial consistency across MTS data. Specifically, we propose graph augmentations including node and edge augmentations to preserve the stability of sensors and their correlations, followed by graph contrasting with both node- and graph-level contrasting to extract robust sensor- and global-level features. We further introduce multi-window temporal contrasting to ensure temporal consistency in the data for each sensor. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on various MTS classification tasks. The code is available at https://github.com/Frank-Wang-oss/TS-GAC.

Figures (7)

• Figure 1: Signals from knee and foot for walking and running. Foot is more important for classification due to its large amplitude. (a) During walking, both knee and foot have low frequency and amplitude. (b) During running, both sensors show increased frequency and amplitude. Disturbances in the foot sensor, like insensitivity, may cause running signals to have a similar amplitude to walking signals, which may mislead a classifier and mis-classify running as walking.
• Figure 2: Overall structure of TS-GAC. (1) Graph augmentations to augment MTS data effectively, generating weak and strong views. The graph augmentations involve node and edge augmentations, where node augmentations include both frequency and temporal augmentations to fully augment sensors. Node frequency augmentations are first applied, followed by segmenting augmented samples into multiple windows by considering the dynamic local patterns in MTS data. Node temporal augmentations are utilized within each window, followed by 1D-CNN to process these windows. Subsequently, graphs are constructed and augmented through edge augmentations, and then processed by GNN. (2) Graph contrasting includes NC and GC to achieve spatial consistency. NC ensures robust sensors by pulling closer corresponding sensors in different views and pushing father different sensors in those views within each sample. GC ensures robust global features by pulling closer corresponding samples in different views and pushing father different samples in those views within each batch. MWTC further achieves temporal consistency for each sensor by summarizing past windows to contrast with future windows in another view.
• Figure 3: The multi-window segmentation to generate multiple windows for one MTS sample.
• Figure 4: Visualization for sensor features.
• Figure 5: Visualization for spatial consistency.