Abstract
Temporal Domain Generalization (TDG) has emerged to address real-world streaming data with distribution shifts over time. However, existing methods are either prone to overfitting to domain-specific noise in the data space or become overly complex and less interpretable in the parameter space. To bridge these gaps, we propose \textbf{AdaSpecK}, a spectral-Koopman framework with adaptive context extraction for TDG. To mitigate noise fitting to irregularly sampled domains, we introduce spectral-regularized Koopman dynamics modeling, which applies spectral-aware filtering in the latent space to extract denoised low-frequency trajectories and learn a Koopman operator to model the system dynamics in a linearized space. To model complex historical environments under non-stationarity, we design a context-informed heterogeneous pattern extraction mechanism. Specifically, we employ a target-conditioned attention module to attend to distinct past windows, producing a dynamic, target-specific historical summary. By constructing an environmental signature from the current evolutionary pattern, our model adaptively perceives which aspects of the past context are most informative for future prediction via a learned router. Extensive experiments on eight diverse classification and regression benchmarks demonstrate that AdaSpecK achieves state-of-the-art performance. The code and datasets are available at \href{}{https://anonymous.4open.science/r/Ada-Spec-K}.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zhang, T., Ke, Y., Shu, Y., Sun, C., An, Y., Guo, C., & Yang, B. (2026). Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization. https://omanscience.com/en/articles/adaptive-spectral-koopman-dynamics-modeling-for-temporal-domain-generalization
MLA 9
Zhang, Tengxue, et al. "Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization." https://omanscience.com/en/articles/adaptive-spectral-koopman-dynamics-modeling-for-temporal-domain-generalization.
Chicago (author–date)
Zhang, Tengxue, Yu Ke, Yang Shu, Chenchen Sun, Yisheng An, Chenjuan Guo, and Bin Yang. 2026. "Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization." https://omanscience.com/en/articles/adaptive-spectral-koopman-dynamics-modeling-for-temporal-domain-generalization.
Harvard
Zhang, T., Ke, Y., Shu, Y., Sun, C., An, Y., Guo, C. and Yang, B. (2026) 'Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization', Available at: https://omanscience.com/en/articles/adaptive-spectral-koopman-dynamics-modeling-for-temporal-domain-generalization.
Vancouver
Zhang T, Ke Y, Shu Y, Sun C, An Y, Guo C, et al. Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization. https://omanscience.com/en/articles/adaptive-spectral-koopman-dynamics-modeling-for-temporal-domain-generalization
IEEE
T. Zhang, Y. Ke, Y. Shu, C. Sun, Y. An, C. Guo, and B. Yang, "Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization," https://omanscience.com/en/articles/adaptive-spectral-koopman-dynamics-modeling-for-temporal-domain-generalization.