Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 5626-5637· 0 citations· 38 references
TL;DR
RePatch is proposed, a two-stage framework that learns adaptive and reusable temporal representations for time series forecasting and achieves state-of-the-art performance on most benchmarks and consistently generalizes well across diverse transfer scenarios.
Abstract
Multivariate time series forecasting is a fundamental yet challenging task due to non-stationary dynamics, evolving temporal structures, and limited generalization across scenarios. Recent patch-based methods improve long-range modeling by segmenting sequences into local units. Still, they typically rely on fixed or weakly adaptive patching strategies and continuous latent representations, which limit flexibility and pattern reuse. In this paper, we propose RePatch, a two-stage framework that learns adaptive and reusable temporal representations for time series forecasting. During self-supervised pretraining, RePatch introduces a Dynamic Patcher that adaptively segments time series into variable-length patches guided by an entropy-based objective, enabling precise alignment with local temporal dynamics. A Temporal Interaction Module further captures both local and global temporal dependencies and maps the resulting representations into a structured discrete latent space via vector quantization. The learned discrete representations provide a compact and transferable abstraction that naturally supports token-based sequence modeling for downstream forecasting. Extensive experiments across 14 real-world datasets demonstrate that RePatch achieves state-of-the-art performance on most benchmarks and consistently generalizes well across diverse transfer scenarios.
Generative modeling has shown strong promise for multivariate time mseries (MTS) forecasting, especially scale to high-dimensional settings. Diffusion-based methods achieve competitive performance but typically require many sampling steps at inference. VAE-based non-iterative forecasting frameworks have therefore emerg...
Shi-Bo Feng, Wan-Jin Feng, Yang Qiu et al.· 0 citations
This work proposes MUSE, a dependency-aware adaptation framework built on a fully frozen pretrained MAE, which performs lightweight refinement at different encoder depths and explicitly models across-period temporal dependencies and within-period periodic dependencies.
Xin-Ying Cai, Jun-Kai Lu, Yu-Han Zhu et al.· 0 citations
FreKoo++ is proposed, a novel continuous spectral-dynamical framework that pioneers the unification of continuous Koopman modal dynamics with adaptive spectral disentanglement and derives modal approximation and generalization bounds that characterize how amplitude and eigenvalue estimation errors propagate with the pr...
En-Shui Yu, Xiao-Yu Yang, Wei Duan et al.· 0 citations
This work defines cross-modal attention as a selection process, where semantic prompts are employed to induce a sparse temporal attribution distribution over temporal positions and employs low-entropy regularization alongside global cross-modal consistency constraints to regulate the selection behavior.
Xue-Yun Luo, Qiang Lu, Sangui Jian et al.· Proceedings of the Thirty-Fi...· 0 citations
Time series foundation models (TSFMs) have recently delivered impressive zero-shot performance across diverse forecasting tasks. However, real-world decision-making frequently relies on \emph{irregular multivariate time series} (IMTS), where inconsistent inter-observation intervals and asynchronous sampling across vari...
The findings indicate that passing attention-derived context into a bidirectional memory module offers a practical means of combining long-horizon structure with local temporal variation, although computational cost remains relevant for latency-sensitive trading applications.
Hao Wu· AI and Data Science Journal· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.