How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Control
This work addresses the problem of flexible time series editing for applications like human-in-the-loop generation, though it appears incremental as it builds on existing diffusion-based models.
The paper tackles the challenge of controlling properties in generated time series sequences by introducing the CocktailEdit framework, which enables precise modifications with multi-grained control while preserving temporal coherence, achieving effective results across diverse datasets and models.
Recent advances in time series generation have shown promise, yet controlling properties in generated sequences remains challenging. Time Series Editing (TSE) - making precise modifications while preserving temporal coherence - consider both point-level constraints and segment-level controls that current methods struggle to provide. We introduce the CocktailEdit framework to enable simultaneous, flexible control across different types of constraints. This framework combines two key mechanisms: a confidence-weighted anchor control for point-wise constraints and a classifier-based control for managing statistical properties such as sums and averages over segments. Our methods achieve precise local control during the denoising inference stage while maintaining temporal coherence and integrating seamlessly, with any conditionally trained diffusion-based time series models. Extensive experiments across diverse datasets and models demonstrate its effectiveness. Our work bridges the gap between pure generative modeling and real-world time series editing needs, offering a flexible solution for human-in-the-loop time series generation and editing. The code and demo are provided for validation.