SeriesGAN: Time Series Generation via Adversarial and Autoregressive Learning
This work addresses the problem of generating realistic time series data for applications like finance or healthcare, though it appears incremental as it builds on existing GAN and autoencoder methods.
The paper tackles challenges in GAN-based time series generation, such as suboptimal convergence and information loss, by introducing a dual-discriminator framework that integrates autoencoder embeddings and adversarial training, resulting in high-fidelity data that outperforms state-of-the-art benchmarks on real and synthetic datasets.
Current Generative Adversarial Network (GAN)-based approaches for time series generation face challenges such as suboptimal convergence, information loss in embedding spaces, and instability. To overcome these challenges, we introduce an advanced framework that integrates the advantages of an autoencoder-generated embedding space with the adversarial training dynamics of GANs. This method employs two discriminators: one to specifically guide the generator and another to refine both the autoencoder's and generator's output. Additionally, our framework incorporates a novel autoencoder-based loss function and supervision from a teacher-forcing supervisor network, which captures the stepwise conditional distributions of the data. The generator operates within the latent space, while the two discriminators work on latent and feature spaces separately, providing crucial feedback to both the generator and the autoencoder. By leveraging this dual-discriminator approach, we minimize information loss in the embedding space. Through joint training, our framework excels at generating high-fidelity time series data, consistently outperforming existing state-of-the-art benchmarks both qualitatively and quantitatively across a range of real and synthetic multivariate time series datasets.