Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN)
This addresses data sharing challenges in sensitive domains like healthcare and finance by improving synthetic data quality for machine learning applications, though it is an incremental advancement over existing GAN methods.
The paper tackled the problem of generating multivariate time series with complex inter-channel dynamics from a single source, such as medical or financial data, by proposing COSCI-GAN, which uses a common latent space point and a central discriminator to preserve correlations, resulting in synthetic data that performs very well in downstream tasks.
Generating multivariate time series is a promising approach for sharing sensitive data in many medical, financial, and IoT applications. A common type of multivariate time series originates from a single source such as the biometric measurements from a medical patient. This leads to complex dynamical patterns between individual time series that are hard to learn by typical generation models such as GANs. There is valuable information in those patterns that machine learning models can use to better classify, predict or perform other downstream tasks. We propose a novel framework that takes time series' common origin into account and favors channel/feature relationships preservation. The two key points of our method are: 1) the individual time series are generated from a common point in latent space and 2) a central discriminator favors the preservation of inter-channel/feature dynamics. We demonstrate empirically that our method helps preserve channel/feature correlations and that our synthetic data performs very well in downstream tasks with medical and financial data.