{"id":1048293,"date":"2024-06-17T20:46:11","date_gmt":"2024-06-18T03:46:11","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-blog-post&p=1048293"},"modified":"2024-06-17T20:53:07","modified_gmt":"2024-06-18T03:53:07","slug":"mg-tsd-advancing-time-series-analysis-with-multi-granularity-guided-diffusion-model","status":"publish","type":"msr-blog-post","link":"https:\/\/www.microsoft.com\/en-us\/research\/articles\/mg-tsd-advancing-time-series-analysis-with-multi-granularity-guided-diffusion-model\/","title":{"rendered":"MG-TSD: Advancing time series analysis with multi-granularity guided diffusion model"},"content":{"rendered":"\n
Author: Chang Xu<\/a><\/em><\/p>\n\n\n\n Diffusion probabilistic models have the capacity to generate high-fidelity samples for generative time series forecasting. However, they also present issues of instability due to their stochastic nature. In order to tackle this challenge, researchers from Microsoft Research Asia introduce a novel approach called \u201cMG-TSD\u201d. The paper \u201cMG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process (opens in new tab)<\/span><\/a>\u201d, presented at ICLR 2024, capitalizes on the intrinsic granularity levels present in the data, utilizing them as predefined targets at various stages of the diffusion process. The aforementioned targets are employed to guide the learning trajectory of the diffusion models, thereby ensuring a more stable and accurate forecast.<\/p>\n\n\n\n It is noteworthy that the MG-TSD method yields remarkable outcomes without the necessity of additional data. In the field of long-term forecasting, researchers have established a new state-of-the-art methodology that demonstrates a notable relative improvement across six benchmarks with improvement ranging from 4.7% to 35.8%.<\/p>\n\n\n\n It can be observed that the forward process of the diffusion model, which sequentially corrupts the data distribution to a standard normal distribution, intuitively aligns with the process of smoothing fine-grained data into a coarser-grained representation. Both of these processes result in a gradual loss of finer distribution features. This suggests that intrinsic features within data granularities may also serve as a source of guidance.<\/p>\n\n\n\nGuiding diffusion processes through intrinsic data granularities features in time series data<\/h2>\n\n\n\n