FDNet: Focal Decomposed Network for Efficient, Robust and Practical time series forecasting

Li Shen, Yuning Wei, Yangzhu Wang

Keywords: Time series Forecasting, Deep Learning, Neural Networks

TL;DR: A Focal Decomposed Network for efficient, robust and practical time series forecasting

Abstract: 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 and competitive upon theoretical basis. (2) By abandoning global coarse-grained feature maps, FDNet overcomes distribution shift problem caused by changing local dynamics of time series which is common in real-world applications. (3) FDNet is not dependent on any assumption or priori knowledge of time series except basic auto-regression, which makes 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 LSTI problem. FDNet achieves promising forecasting performances on five benchmark datasets and reduces prediction MSE by 38.4% on average compared with other seven SOTA forecasting baselines.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2306.10703/code)