StateFlow: 用于长时域时间序列预测的双状态循环建模
StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting
AI总结：
提出StateFlow框架，扩展VARNN为双状态循环骨干，结合隐藏状态轨迹和残差记忆轨迹，通过分块解码器和两阶段优化实现长时域多步预测，在基准上取得竞争性能。
摘要：
长时域多变量时间序列预测（LTSF）由于非平稳性、状态转移和误差累积仍然具有挑战性。变异性感知递归神经网络（VARNN）通过维护由一步预测误差驱动的残差记忆状态来跟踪这种变异性。然而，其原始公式仅限于一步序列回归，并不直接支持多步预测。在这项工作中，我们将VARNN扩展到长时域预测，并引入StateFlow，一种递归预测框架，使用VARNN作为双状态循环骨干，从回溯序列中捕获两个互补信号：表示主要时间动态（包括趋势、季节性、水平变化和重复模式）的隐藏状态轨迹，以及由一步基预测与观测值之间的误差的非线性递归变换驱动的、表示结构化局部预测偏差的残差记忆轨迹。一个基于分块的解码器分别总结这些轨迹，并将它们映射到未来时域以进行直接多步预测。我们进一步采用两阶段优化策略，首先通过一步基预测目标训练VARNN编码器，以优化回溯序列上的内部表示，然后训练一个特定于时域的解码器进行直接多步预测。在标准LTSF基准上的实验表明，StateFlow在保持线性递归编码和紧凑模型设计的同时，对强线性、递归、卷积和基于Transformer的基线实现了竞争性能。
英文摘要：
Long-horizon multivariate time series forecasting (LTSF) remains challenging due to non-stationarity, regime shifts, and error accumulation. The Variability-Aware Recursive Neural Network (VARNN) is designed to track such variability by maintaining a residual-memory state driven by one-step prediction errors. However, its original formulation is limited to one-step sequence regression and does not directly support multi-step forecasting. In this work, we extend VARNN to long-horizon forecasting and introduce StateFlow, a recurrent forecasting framework that uses VARNN as a dual-state recurrent backbone to capture two complementary signals from the lookback sequence: a hidden-state trajectory representing primary temporal dynamics, including trend, seasonality, level changes, and recurring patterns, and a residual-memory trajectory representing structured local prediction deviations, driven from a nonlinear recurrent transformation of errors between one-step base predictions and observed values. A chunk-based decoder separately summarizes these trajectories and maps them to the future horizon for direct multi-step forecasting. We further employ a two-stage optimization strategy that first trains the VARNN encoder through a one-step base prediction objective to optimize the internal representations over the lookback sequence, and then trains a horizon-specific decoder for direct multi-step forecasting. Experiments on standard LTSF benchmarks show that StateFlow achieves competitive performance against strong linear, recurrent, convolutional, and Transformer-based baselines while preserving linear recurrent encoding and a compact model design.
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。
