Temporal-Frequency Co-training for Time Series Semi-supervised Learning


  • Zhen Liu South China University of Technology
  • Qianli Ma South China University of Technology
  • Peitian Ma South China University of Technology
  • Linghao Wang South China University of Technology




ML: Time-Series/Data Streams, ML: Representation Learning, ML: Semi-Supervised Learning


Semi-supervised learning (SSL) has been actively studied due to its ability to alleviate the reliance of deep learning models on labeled data. Although existing SSL methods based on pseudo-labeling strategies have made great progress, they rarely consider time-series data's intrinsic properties (e.g., temporal dependence). Learning representations by mining the inherent properties of time series has recently gained much attention. Nonetheless, how to utilize feature representations to design SSL paradigms for time series has not been explored. To this end, we propose a Time Series SSL framework via Temporal-Frequency Co-training (TS-TFC), leveraging the complementary information from two distinct views for unlabeled data learning. In particular, TS-TFC employs time-domain and frequency-domain views to train two deep neural networks simultaneously, and each view's pseudo-labels generated by label propagation in the representation space are adopted to guide the training of the other view's classifier. To enhance the discriminative of representations between categories, we propose a temporal-frequency supervised contrastive learning module, which integrates the learning difficulty of categories to improve the quality of pseudo-labels. Through co-training the pseudo-labels obtained from temporal-frequency representations, the complementary information in the two distinct views is exploited to enable the model to better learn the distribution of categories. Extensive experiments on 106 UCR datasets show that TS-TFC outperforms state-of-the-art methods, demonstrating the effectiveness and robustness of our proposed model.




How to Cite

Liu, Z., Ma, Q., Ma, P., & Wang, L. (2023). Temporal-Frequency Co-training for Time Series Semi-supervised Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 37(7), 8923-8931. https://doi.org/10.1609/aaai.v37i7.26072



AAAI Technical Track on Machine Learning II