FM-TS: Flow Matching for Time Series Generation

ICLR 2025 Conference Submission827 Authors

Keywords: Time Series Generation, Flow Matching, Generative AI

TL;DR: We introduce FM-TS, a groundbreaking flow matching framework for time series generation that achieves state-of-the-art performance in both conditional and unconditional settings.

Abstract:

Time series generation has emerged as an essential tool for analyzing temporal data across numerous fields.
While diffusion models have recently gained significant attention in generating high-quality time series, they tend to be computationally demanding and reliant on complex stochastic processes.
To address these limitations, we introduce FM-TS, a rectified Flow Matching-based framework for Time Series generation, which simplifies the time series generation process by directly optimizing continuous trajectories. This approach avoids the need for iterative sampling or complex noise schedules typically required in diffusion-based models.
FM-TS is more efficient in terms of training and inference.
Moreover, FM-TS is highly adaptive, supporting both conditional and unconditional time series generation.
Notably, through our novel inference design, the model trained in an unconditional setting can seamlessly generalize to conditional tasks without the need for retraining. Extensive benchmarking across both settings demonstrates that FM-TS consistently delivers superior performance compared to existing approaches while being more efficient in terms of training and inference.
For instance, in terms of discriminative score, FM-TS achieves $0.005$, $0.019$, $0.011$, $0.005$, $0.053$, and $0.106$ on the Sines, Stocks, ETTh, MuJoCo, Energy, and fMRI unconditional time series datasets, respectively, significantly outperforming the second-best method which achieves $0.006$, $0.067$, $0.061$, $0.008$, $0.122$, and $0.167$ on the same datasets.
We have achieved superior performance in solar forecasting and MuJoCo imputation tasks, significantly enhanced by our innovative $t$ power sampling method.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 827