Search papers, labs, and topics across Lattice.
This paper introduces DynG-Diff, a dynamic guidance diffusion framework designed for probabilistic multivariate time series forecasting that addresses the challenges of information heterogeneity and variable reliability. By employing a two-stage training strategy and a state-aware policy network, DynG-Diff effectively models the joint distribution of time series data while adaptively adjusting guidance based on real-time noise levels. Experimental results show that DynG-Diff outperforms existing conditional diffusion models in forecasting accuracy and robustness against observation corruption.
DynG-Diff achieves superior probabilistic forecasting by dynamically adjusting guidance based on real-time variable reliability, outperforming traditional methods in noisy environments.
Probabilistic multivariate time series (MTS) forecasting is crucial for modeling complex dynamical systems. However, existing diffusion-based methods rely on task-specific conditional paradigms that lack flexibility and struggle with inherent"information heterogeneity"--the significantly varying noise levels and evolutionary patterns across variables. To address this, we propose DynG-Diff, a variable-sensitive dynamic guidance diffusion framework for probabilistic multivariate time-series forecasting: (1) DynG-Diff adopts a two-stage separated training strategy and uses an unconditional diffusion backbone to model the joint distribution of multivariate time series. (2) DynG-Diff introduces a lightweight state-aware policy network that adaptively infers variable reliability from real-time noisy states and one-step denoising estimates, outputting a dynamic guidance strength matrix. (3) DynG-Diff mathematically formulates this dynamic weight as the local precision of the observation distribution, enabling precise guidance for high-confidence variables during inference while filtering out interference from anomalous noise. Extensive experiments on real-world benchmarks demonstrate competitive probabilistic forecasting performance against state-of-the-art conditional diffusion models and improved robustness under severe observation corruption.The implementation code is available at: https://github.com/TT-20011031/DynG-Diff
