TCGAN: Convolutional Generative Adversarial Network for Time Series Classification and Clustering
This work addresses the problem of costly and infeasible labeled data acquisition for time series recognition, offering a general-purpose solution for researchers and practitioners in fields like finance or healthcare, though it is incremental as it adapts GANs to time series.
The paper tackles the challenge of learning representations from time series data without requiring large labeled datasets by introducing TCGAN, a convolutional GAN that uses one-dimensional CNNs for unsupervised learning, resulting in faster and more accurate performance than existing time-series GANs and enabling simple classification and clustering methods to achieve superior and stable performance.
Recent works have demonstrated the superiority of supervised Convolutional Neural Networks (CNNs) in learning hierarchical representations from time series data for successful classification. These methods require sufficiently large labeled data for stable learning, however acquiring high-quality labeled time series data can be costly and potentially infeasible. Generative Adversarial Networks (GANs) have achieved great success in enhancing unsupervised and semi-supervised learning. Nonetheless, to our best knowledge, it remains unclear how effectively GANs can serve as a general-purpose solution to learn representations for time series recognition, i.e., classification and clustering. The above considerations inspire us to introduce a Time-series Convolutional GAN (TCGAN). TCGAN learns by playing an adversarial game between two one-dimensional CNNs (i.e., a generator and a discriminator) in the absence of label information. Parts of the trained TCGAN are then reused to construct a representation encoder to empower linear recognition methods. We conducted comprehensive experiments on synthetic and real-world datasets. The results demonstrate that TCGAN is faster and more accurate than existing time-series GANs. The learned representations enable simple classification and clustering methods to achieve superior and stable performance. Furthermore, TCGAN retains high efficacy in scenarios with few-labeled and imbalanced-labeled data. Our work provides a promising path to effectively utilize abundant unlabeled time series data.