SOURCE-LINKED INTELLIGENCE

When Does Adversarial Refinement Help? A Negative Result and Open Problem in Adapting R3GAN to Time Series Imputation

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Diffusion models and transformers have supplanted GANs for multivariate time series imputation, largely on grounds of GAN training instability. R3GAN (NeurIPS 2024) removes that instability via regularized relativistic losses with provable convergence, raising a natural question: do stable, modern GANs revive adversarial imputation? We adapt R3GAN to 1D temporal data with a coarse-to-fine refinement framework and a frequency-domain discriminator, and audit 14 saved configurations across 3 datasets. Because these are heterogeneous single runs, the evidence is descriptive rather than a matched c

Read original source ↗ Open in workspace

recordType

paper

region

Global