AimTS: Augmented Series and Image Contrastive Learning for Time Series Classification
This addresses the challenge of domain divergence and limited data in time series classification, though it is incremental as it builds on pre-training and contrastive learning paradigms.
The paper tackles the problem of time series classification (TSC) suffering from accuracy degradation due to insufficient training samples in certain domains by introducing AimTS, a pre-training framework that uses augmented series and image contrastive learning, achieving good generalization performance and enabling efficient and few-shot learning on various downstream datasets.
Time series classification (TSC) is an important task in time series analysis. Existing TSC methods mainly train on each single domain separately, suffering from a degradation in accuracy when the samples for training are insufficient in certain domains. The pre-training and fine-tuning paradigm provides a promising direction for solving this problem. However, time series from different domains are substantially divergent, which challenges the effective pre-training on multi-source data and the generalization ability of pre-trained models. To handle this issue, we introduce Augmented Series and Image Contrastive Learning for Time Series Classification (AimTS), a pre-training framework that learns generalizable representations from multi-source time series data. We propose a two-level prototype-based contrastive learning method to effectively utilize various augmentations in multi-source pre-training, which learns representations for TSC that can be generalized to different domains. In addition, considering augmentations within the single time series modality are insufficient to fully address classification problems with distribution shift, we introduce the image modality to supplement structural information and establish a series-image contrastive learning to improve the generalization of the learned representations for TSC tasks. Extensive experiments show that after multi-source pre-training, AimTS achieves good generalization performance, enabling efficient learning and even few-shot learning on various downstream TSC datasets.