发表机构
Institute of Artificial Intelligence, University of Science and Technology Beijing; Key Laboratory of Intelligent Bionic Unmanned Systems, Ministry of Education, University of Science and Technology Beijing; School of Artificial Intelligence, University of Science and Technology Beijing（北京科技大学人工智能研究院; 北京科技大学智能仿生无人系统重点实验室; 北京科技大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出轻量级插件模块CARE，无需重新设计架构即可增强确定性时间序列预测器，通过多目标损失优化提升精度，风险门可识别高误差区域，在八个基准测试中以低开销实现性能提升。
AI 中文摘要
多变量长期预测对电力负荷调度、交通流量管理及金融风险控制至关重要。现有确定性骨干网络输出单一轨迹，掩盖了不同预测步长和通道间的异质性预测难度，且未提供局部可靠性信号。我们提出CARE（带对齐上下文与相对误差估计的校正分支），这是一种轻量级插件，无需重新设计架构即可增强任何确定性预测器。CARE与基础模型并行运行，对历史上下文进行重采样以匹配预测步长，从该对齐历史中学习残差校正模式，并应用由逐坐标sigmoid风险门调控的感知尺度有界更新。多目标损失函数联合优化预测精度、残差跟踪、风险对齐及基础模型锚定。在包含三种代表性骨干网络的八个基准测试中，CARE以极少的参数和延迟开销提升了精度。其风险门可可靠识别高误差区域：在Weather数据集上，最高门控三分位的误差约为最低门控三分位的四倍，为规划者提供了可解释的逐步信任信号。代码可在指定URL获取。
英文摘要
Multivariate long-horizon forecasting is critical to electricity load scheduling and traffic flow management, and to financial risk control. Existing deterministic backbones output a single trajectory, masking heterogeneous prediction difficulty across horizons and channels and providing no localized reliability signal. We present CARE (Corrective branch with Aligned context and Relative-error Estimation), a lightweight plug-in that enhances any deterministic forecaster without architectural redesign. Operating in parallel with the base model, CARE resamples historical context to match the forecast horizon, learns residual correction patterns from this aligned history, and applies scale-aware bounded updates modulated by per-coordinate sigmoid risk gates. A multi-objective loss jointly optimizes forecast accuracy, residual tracking, risk alignment, and base-model anchoring. Across eight benchmarks with three representative backbones, CARE improves accuracy with marginal parameter and latency overhead. Its risk gates reliably identify high-error regions: on Weather, the highest-gate tertile exhibits nearly four times the error of the lowest-gate tertile, offering planners an interpretable per-step trust signal. Code is available at https://github.com/CG-BNYC/CARE.
Comments15pages, 2figures
