TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts
This addresses the problem of multi-domain time series generation for applications like data augmentation and privacy, representing a novel method for a known bottleneck.
The paper tackles the challenge of generating time series data across multiple domains by introducing TimeDP, a diffusion model that uses domain prompts and a semantic prototype module, achieving state-of-the-art in-domain quality and strong performance in unseen domains.
Time series generation models are crucial for applications like data augmentation and privacy preservation. Most existing time series generation models are typically designed to generate data from one specified domain. While leveraging data from other domain for better generalization is proved to work in other application areas, this approach remains challenging for time series modeling due to the large divergence in patterns among different real world time series categories. In this paper, we propose a multi-domain time series diffusion model with domain prompts, named TimeDP. In TimeDP, we utilize a time series semantic prototype module which defines time series prototypes to represent time series basis, each prototype vector serving as "word" representing some elementary time series feature. A prototype assignment module is applied to extract the extract domain specific prototype weights, for learning domain prompts as generation condition. During sampling, we extract "domain prompt" with few-shot samples from the target domain and use the domain prompts as condition to generate time series samples. Experiments demonstrate that our method outperforms baselines to provide the state-of-the-art in-domain generation quality and strong unseen domain generation capability.