TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation
This addresses the problem of data scarcity and noise in time series for domains like forecasting and anomaly detection, representing an incremental improvement through hybrid methods.
The paper tackled the challenge of generating high-quality synthetic time series by proposing TIMED, a framework that integrates diffusion models, autoregressive supervision, and adversarial feedback, resulting in more realistic and temporally coherent sequences than state-of-the-art models across diverse benchmarks.
Generating high-quality synthetic time series is a fundamental yet challenging task across domains such as forecasting and anomaly detection, where real data can be scarce, noisy, or costly to collect. Unlike static data generation, synthesizing time series requires modeling both the marginal distribution of observations and the conditional temporal dependencies that govern sequential dynamics. We propose TIMED, a unified generative framework that integrates a denoising diffusion probabilistic model (DDPM) to capture global structure via a forward-reverse diffusion process, a supervisor network trained with teacher forcing to learn autoregressive dependencies through next-step prediction, and a Wasserstein critic that provides adversarial feedback to ensure temporal smoothness and fidelity. To further align the real and synthetic distributions in feature space, TIMED incorporates a Maximum Mean Discrepancy (MMD) loss, promoting both diversity and sample quality. All components are built using masked attention architectures optimized for sequence modeling and are trained jointly to effectively capture both unconditional and conditional aspects of time series data. Experimental results across diverse multivariate time series benchmarks demonstrate that TIMED generates more realistic and temporally coherent sequences than state-of-the-art generative models.