Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification
This work addresses the challenge of time-series classification when labeled data is scarce, offering a novel framework that improves representation learning, though it appears incremental by building on existing contrastive methods.
The authors tackled the problem of learning time-series representations with limited labeled data by proposing TS-TCC, a self-supervised contrastive learning framework with temporal and contextual modules, and extended it to CA-TCC for semi-supervised settings. The results show that linear evaluation of learned features performs comparably to fully supervised training, with high efficiency in few-label and transfer learning scenarios.
Learning time-series representations when only unlabeled data or few labeled samples are available can be a challenging task. Recently, contrastive self-supervised learning has shown great improvement in extracting useful representations from unlabeled data via contrasting different augmented views of data. In this work, we propose a novel Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC) that learns representations from unlabeled data with contrastive learning. Specifically, we propose time-series-specific weak and strong augmentations and use their views to learn robust temporal relations in the proposed temporal contrasting module, besides learning discriminative representations by our proposed contextual contrasting module. Additionally, we conduct a systematic study of time-series data augmentation selection, which is a key part of contrastive learning. We also extend TS-TCC to the semi-supervised learning settings and propose a Class-Aware TS-TCC (CA-TCC) that benefits from the available few labeled data to further improve representations learned by TS-TCC. Specifically, we leverage the robust pseudo labels produced by TS-TCC to realize a class-aware contrastive loss. Extensive experiments show that the linear evaluation of the features learned by our proposed framework performs comparably with the fully supervised training. Additionally, our framework shows high efficiency in the few labeled data and transfer learning scenarios. The code is publicly available at \url{https://github.com/emadeldeen24/CA-TCC}.