[2511.11991] ReCast: Reliability-aware Codebook Assisted Lightweight Time Series Forecasting

Computer Science > Machine Learning arXiv:2511.11991 (cs) [Submitted on 15 Nov 2025 (v1), last revised 5 Mar 2026 (this version, v3)] Title:ReCast: Reliability-aware Codebook Assisted Lightweight Time Series Forecasting Authors:Xiang Ma, Taihua Chen, Pengcheng Wang, Xuemei Li, Caiming Zhang View a PDF of the paper titled ReCast: Reliability-aware Codebook Assisted Lightweight Time Series Forecasting, by Xiang Ma and 4 other authors View PDF HTML (experimental) Abstract:Time series forecasting is crucial for applications in various domains. Conventional methods often rely on global decomposition into trend, seasonal, and residual components, which become ineffective for real-world series dominated by local, complex, and highly dynamic patterns. Moreover, the high model complexity of such approaches limits their applicability in real-time or resource-constrained environments. In this work, we propose a novel \textbf{RE}liability-aware \textbf{C}odebook-\textbf{AS}sisted \textbf{T}ime series forecasting framework (\textbf{ReCast}) that enables lightweight and robust prediction by exploiting recurring local shapes. ReCast encodes local patterns into discrete embeddings through patch-wise quantization using a learnable codebook, thereby compactly capturing stable regular structures. To compensate for residual variations not preserved by quantization, ReCast employs a dual-path architecture comprising a quantization path for efficient modeling of regular structures and a residua...