[3Win5] Poster session 3

[3Win5-26] Iterative Decoding Strategies for Diffusion Models based on Empirically Estimated Uncertainty for Time Series Forecasting

〇Koki Ueno¹, Kohei Makino¹, Yutaka Sasaki¹ (1.Toyota Technological Institute)

Keywords:Time series forecasting, Diffusion Model, Decoding Strategy

Diffusion models have made remarkable advancements in various data generation tasks; however, their performance in time series forecasting, which is a task to forecast future series from past series, remains inferior to other existing approaches. To address this, this paper focuses on enhancing the performance of diffusion model-based time series forecasting. Our preliminary experiments revealed that diffusion model outputs tend to deviate from the ground truth series. To mitigate this issue, it is crucial to generate forecast series that remain close to the gold series. Motivated by the uncertainty sampling technique in active learning, we propose EUGID (Empirically estimated Uncertainty-Guided Iterative Decoding strategy), a novel decoding strategy for diffusion-model forecasting based on an estimated uncertainty distribution. Specifically, it iteratively reproduces the uncertainty distribution through a forward diffusion process and generates forecast series via a reverse diffusion process. EUGID significantly improves forecasting performance, outperforming existing diffusion-based methods on seven out of eight benchmark datasets.