Retrieval-Augmented Diffusion Models for Time Series Forecasting
This work addresses performance issues in time series forecasting for applications requiring stable predictions, but it is incremental as it builds on existing diffusion models with a retrieval mechanism.
The paper tackles the instability and guidance deficiencies in time series diffusion models by proposing a retrieval-augmented diffusion model (RATD) that uses retrieved references to guide denoising, showing effectiveness in complicated prediction tasks across multiple datasets.
While time series diffusion models have received considerable focus from many recent works, the performance of existing models remains highly unstable. Factors limiting time series diffusion models include insufficient time series datasets and the absence of guidance. To address these limitations, we propose a Retrieval- Augmented Time series Diffusion model (RATD). The framework of RATD consists of two parts: an embedding-based retrieval process and a reference-guided diffusion model. In the first part, RATD retrieves the time series that are most relevant to historical time series from the database as references. The references are utilized to guide the denoising process in the second part. Our approach allows leveraging meaningful samples within the database to aid in sampling, thus maximizing the utilization of datasets. Meanwhile, this reference-guided mechanism also compensates for the deficiencies of existing time series diffusion models in terms of guidance. Experiments and visualizations on multiple datasets demonstrate the effectiveness of our approach, particularly in complicated prediction tasks.