提出双流残差提升方法，显著增强时间序列预测对概念漂移的鲁棒性。
DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting
- 采用双流结构与残差递减机制，逐层重构内在信号
- 在多个数据集上平均性能提升15.8%，超越现有方法
- 适合需要高鲁棒性的工业级时间序列预测场景
时间序列具有明显的非平稳性，导致大多数预测方法在概念漂移下表现下降，即使使用实例归一化亦然。本文通过偏差-方差视角分析概念漂移，证明加权集成可降低方差而不增加偏差。据此提出DeepBooTS，一种端到端的双流残差递减提升方法，能逐步重构内在信号。模型中每个深度块作为一组学习器，辅以输出分支形成通往最终预测的高速通道，块间输出修正前序块的残差，实现输入与目标的动态分解。该方法提升泛化能力与可解释性，并显著增强对概念漂移的鲁棒性。大规模实验表明，所提方法在多个数据集上平均性能提升15.8%，确立时间序列预测新基准。
原文摘要 · Abstract (English)
Time-Series (TS) exhibits pronounced non-stationarity. Consequently, most forecasting methods display compromised robustness to concept drift, despite the prevalent application of instance normalization. We tackle this challenge by first analysing concept drift through a bias-variance lens and proving that weighted ensemble reduces variance without increasing bias. These insights motivate DeepBooTS, a novel end-to-end dual-stream residual-decreasing boosting method that progressively reconstructs the intrinsic signal. In our design, each block of a deep model becomes an ensemble of learners with an auxiliary output branch forming a highway to the final prediction. The block-wise outputs correct the residuals of previous blocks, leading to a learning-driven decomposition of both inputs and targets. This method enhances versatility and interpretability while substantially improving robustness to concept drift. Extensive experiments, including those on large-scale datasets, show that the proposed method outperforms existing methods by a large margin, yielding an average performance improvement of 15.8% across various datasets, establishing a new benchmark for TS forecasting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。