Robust Inter-Series Dependency Modeling for Time Series Forecasting via Information-Theoretic Alignment
Lists
Only you see this
Abstract
While iTransformer pioneered general inter-variate dependency (IVD) modeling in Transformers for multivariate time series forecasting (MTSF), subsequent research on such universal paradigms has been surprisingly scarce. Through comprehensive analysis, we identify a critical structural inconsistency in Variate Transformers: typically capturing inter-variate dependencies via shallow self-attention layers while neglecting the critical requirement for deep-layer IVD modeling, which causes spurious correlations modeling and difficulties in model optimization. To address these limitations, we propose CGTFra, as a general framework for consistent IVD modeling. Specifically, we reconsider existing timestamp-based modeling and introduce a frequency-domain masking and resampling method for periodicity preservation, which serves as a general strategy for input feature enhancement. Additionally, CGTFra promotes consistent IVD modeling from two perspectives. Initially, a dynamic graph learning framework is integrated into Transformers to explicitly model IVD in deep network layer. Furthermore, grounded in the Information Bottleneck principle, we further propose a consistency-constrained alignment to learn more robust IVD and temporal feature representations. These three core design philosophies of CGTFra can be integrated into any existing Variate Transformer-based framework, and CGTFra achieves superior predictive performance across 13 long- and short-term datasets with high computational efficiency and desirable interpretability. Code is available at https://github.com/05Pikachu24/Consistent-CGTFra.
BibTeX
@inproceedings{yu2026robust,
author = {Wuqing Yu and Weichen Guo and Jian Zhou and Shuyu Luo and Jiacai Zhang},
title = {{Robust Inter-Series Dependency Modeling for Time Series Forecasting via Information-Theoretic Alignment}},
booktitle = {International Conference on Machine Learning},
year = {2026},
url = {https://openreview.net/forum?id=YQPQuHVLLQ},
}Loading related content...