FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation
This work addresses a critical issue in domains such as healthcare and traffic forecasting by enhancing imputation accuracy, though it is incremental as it builds on existing diffusion and Transformer methods.
The paper tackles the problem of multivariate time series imputation, where missing values hinder applications like healthcare and traffic forecasting, by proposing FADTI, a diffusion-based framework that integrates frequency-aware modules and attention mechanisms, achieving state-of-the-art performance with consistent improvements, especially under high missing rates.
Multivariate time series imputation is fundamental in applications such as healthcare, traffic forecasting, and biological modeling, where sensor failures and irregular sampling lead to pervasive missing values. However, existing Transformer- and diffusion-based models lack explicit inductive biases and frequency awareness, limiting their generalization under structured missing patterns and distribution shifts. We propose FADTI, a diffusion-based framework that injects frequency-informed feature modulation via a learnable Fourier Bias Projection (FBP) module and combines it with temporal modeling through self-attention and gated convolution. FBP supports multiple spectral bases, enabling adaptive encoding of both stationary and non-stationary patterns. This design injects frequency-domain inductive bias into the generative imputation process. Experiments on multiple benchmarks, including a newly introduced biological time series dataset, show that FADTI consistently outperforms state-of-the-art methods, particularly under high missing rates. Code is available at https://anonymous.4open.science/r/TimeSeriesImputation-52BF