SeesawNet：面向非平稳时间序列预测的常见与特定依赖平衡建模
SeesawNet: Towards Non-stationary Time Series Forecasting with Balanced Modeling of Common and Specific Dependencies
AI总结：
SeesawNet通过动态平衡常见和实例特定依赖，解决非平稳时间序列预测中的分布偏移问题，提出ASNA模块以捕捉常见和特定依赖，实验表明其优于现有方法。
摘要：
实例归一化（IN）广泛用于非平稳多变量时间序列预测，以减少分布偏移并突出样本间的共同模式。然而，IN可能过度平滑实例特定的结构信息，这对建模时间和跨通道异质性至关重要。尽管先前方法进一步抑制分布差异或尝试恢复时间特定依赖，但往往忽视了一个核心矛盾：如何根据每个实例的非平稳结构自适应地建模常见和实例特定依赖。为此，我们提出了SeesawNet，一种统一架构，能够在时间和通道维度上动态平衡常见和实例特定依赖建模。其核心是自适应平稳-非平稳注意力（ASNA），它从归一化序列中捕捉共同依赖，从原始序列中捕捉特定依赖，并根据实例级非平稳性自适应融合。基于ASNA，SeesawNet交替进行专门的时间和通道关系建模，以联合捕捉长程和跨变量依赖。在多个现实世界基准上的广泛实验表明，SeesawNet在性能上始终优于现有最先进方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
