This paper presents FDNet: a Focal Decomposed Network for efficient, robust and practical time series forecasting. We break away from conventional deep time series forecasting formulas which obtain prediction results from universal feature maps of input sequences. In contrary, FDNet neglects universal correlations of input elements and only extracts fine-grained local features from input sequence. We show that: (1) Deep time series forecasting with only fine-grained local feature maps of input sequence is feasible upon theoretical basis. (2) By abandoning global coarse-grained feature maps, FDNet overcomes distribution shift problem caused by changing dynamics of time series which is common in real-world applications. (3) FDNet is not dependent on any inductive bias of time series except basic auto-regression, making it general and practical. Moreover, we propose focal input sequence decomposition method which decomposes input sequence in a focal manner for efficient and robust forecasting when facing Long Sequence Time series Input (LSTI) problem. FDNet achieves competitive forecasting performances on six real-world benchmarks and reduces prediction MSE by 38.4% on average compared with other thirteen SOTA baselines. The source code is available at https://github.com/OrigamiSL/FDNet.

翻译：本文提出FDNet：一种高效、鲁棒且实用的时间序列聚焦分解网络。我们突破了传统深度时间序列预测范式——即从输入序列的通用特征图中获取预测结果。相反，FDNet忽略输入元素的全局相关性，仅从输入序列中提取细粒度局部特征。我们证明：（1）仅基于输入序列的细粒度局部特征图进行深度时间序列预测在理论上是可行的；（2）通过舍弃全局粗粒度特征图，FDNet克服了实际应用中因时间序列动态变化导致的分布偏移问题；（3）除基本自回归外，FDNet不依赖任何时间序列归纳偏置，具有通用性与实用性。此外，我们提出聚焦输入序列分解方法，通过聚焦式分解输入序列以高效鲁棒应对长序列时间输入（LSTI）问题。在六个真实世界基准测试中，FDNet实现了具有竞争力的预测性能，与另外13个最先进基线相比，预测均方误差平均降低38.4%。源代码已开源至https://github.com/OrigamiSL/FDNet。