Abstract:Instance normalization (IN) is widely used in non-stationary multivariate time series forecasting to reduce distribution shifts and highlight common patterns across samples. However, IN can over-smooth instance-specific structural information that is essential for modeling temporal and cross-channel heterogeneity. While prior methods further suppress distribution discrepancies or attempt to recover temporal specific dependencies, they often ignore a central tension: how to adaptively model common and instance-specific dependency based on each instance's non-stationary structures. To address this dilemma, we propose SeesawNet, a unified architecture that dynamically balances common and instance-specific dependency modeling in both temporal and channel dimensions. At its core is Adaptive Stationary-Nonstationary Attention (ASNA), which captures common dependencies from normalized sequences and specific dependencies from raw sequences, and adaptively fuses them according to instance-level non-stationarity. Built upon ASNA, SeesawNet alternates dedicated temporal and channel relationship modeling to jointly capture long-range and cross-variable dependencies. Extensive experiments on multiple real-world benchmarks demonstrate that SeesawNet consistently outperforms state-of-the-art methods.
| Comments: | Accepted by IJCAI-ECAI 2026, the 35th International Joint Conference on Artificial Intelligence. Code is at this https URL |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.14551 [cs.LG] |
| (or arXiv:2605.14551v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.14551 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yingjie Zhou [view email]
[v1]
Thu, 14 May 2026 08:29:52 UTC (1,625 KB)