TCGAN: Convolutional Generative Adversarial Network for Time Series Classification and Clustering

TL;DR

TCGAN introduces a convolutional GAN framework for time series classification and clustering that learns effective representations without labels, outperforming existing methods in speed and accuracy, especially with limited labeled data.

Contribution

This paper presents TCGAN, a novel convolutional GAN for time series that learns unlabeled representations, enabling improved classification and clustering performance.

Findings

TCGAN is faster and more accurate than existing time-series GANs.

Learned representations improve simple classification and clustering methods.

TCGAN performs well with few-labeled and imbalanced-labeled data.

Abstract

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.