FrAug: Frequency Domain Augmentation for Time Series ForecastingDownload PDF

22 Sept 2022 (modified: 13 Feb 2023)ICLR 2023 Conference Withdrawn SubmissionReaders: Everyone
Keywords: Time series forecasting, Data augmentation, Few shot learning
TL;DR: A frequency domain data augmentation technique for time-series forecasting task
Abstract: Data augmentation (DA) has become a de facto solution to expand training data size for deep learning. With the proliferation of deep models for time series analysis, various time series DA techniques are proposed in the literature, e.g., cropping-, warping-, flipping-, and mixup-based methods. However, these augmentation methods are mainly applicable for time series classification and anomaly detection tasks. In time series forecasting (TSF), we need to model the fine-grained temporal relationship within time series segments so that we could generate faithful forecasting results given data in a look-back window. Existing DA solutions in the time domain would break such relationship, leading to poor forecasting accuracy. To tackle this problem, this paper proposes simple yet effective frequency domain augmentation techniques that ensure the semantic consistency of augmented data-label pairs in forecasting, named FrAug. We conduct comprehensive experiments on eight widely-used benchmarks with several state-of-the-art TSF deep models. Our results show that FrAug can boost the forecasting accuracy of existing models in most cases. Moreover, we show that, FrAug enables models trained with 1\% of the original training data to achieve similar performance to the ones trained on full training data, which is particularly attractive for cold-start forecasting often occurred in real-life applications.
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: Deep Learning and representational learning
Supplementary Material: zip
14 Replies

Loading