FACT: Fine-grained Across-variable Convolution for Multivariate Time Series Forecasting

ICLR 2026 Conference Submission9329 Authors

Keywords: Multivariate time series forecasting, Fine-grained dynamic variable interactions, Multi-dilated depth-wise convolution.

TL;DR: Effective variable interactions modeling from both time and frequency domains; Efficient multi-dilated depth-wise convolution architecture.

Abstract:

Modeling the relationships among variables has become increasingly important, particularly in high-dimensional multivariate time series forecasting tasks. However, most existing methods primarily focus on capturing coarse-grained correlations between variables, overlooking a finer and more dynamic aspect: the variable interactions often manifest differently as time progresses.
To address this limitation, we propose FACT, an Fine-grained Across-variable Convolution architecture for multivariate Time series forecasting that explicitly models fine-grained variable interactions from both the time and frequency domains.
Technically, we introduce a depth-wise convolution block DConvBlock, which leverages a depth-wise convolution architecture with channel-specific kernels to model dynamic variable interactions at each granularity.
To further enhance efficiency, we reconfigure the original one-dimensional variables into a two-dimensional space, reducing the variable distance and the required model layers. Then DConvBlock incorporates multi-dilated 2D convolutions with progressively increasing dilation rates, enabling the model to capture fine-grained and dynamic variable interactions while efficiently attaining a global reception field.
Extensive experiments on twelve benchmark datasets demonstrate that FACT not only achieves state-of-the-art forecasting accuracy but also delivers substantial efficiency gains, significantly reducing both training time and memory consumption compared to attention mechanism. The code is available at https://anonymous.4open.science/r/FACT-MTSF.

Primary Area: learning on time series and dynamical systems

Submission Number: 9329