DVGAN: Stabilize Wasserstein GAN training for time-domain Gravitational Wave physics
This work addresses the need for improved simulation of gravitational wave detector data to enhance source understanding, dataset augmentation, and noise characterization, representing an incremental advancement in domain-specific GAN applications.
The paper tackled the problem of simulating time-domain gravitational wave signals by introducing DVGAN, a three-player Wasserstein GAN with an auxiliary discriminator on signal derivatives, which stabilized training and produced smoother, less distinguishable generated signals that better captured data distributions.
Simulating time-domain observations of gravitational wave (GW) detector environments will allow for a better understanding of GW sources, augment datasets for GW signal detection and help in characterizing the noise of the detectors, leading to better physics. This paper presents a novel approach to simulating fixed-length time-domain signals using a three-player Wasserstein Generative Adversarial Network (WGAN), called DVGAN, that includes an auxiliary discriminator that discriminates on the derivatives of input signals. An ablation study is used to compare the effects of including adversarial feedback from an auxiliary derivative discriminator with a vanilla two-player WGAN. We show that discriminating on derivatives can stabilize the learning of GAN components on 1D continuous signals during their training phase. This results in smoother generated signals that are less distinguishable from real samples and better capture the distributions of the training data. DVGAN is also used to simulate real transient noise events captured in the advanced LIGO GW detector.