FreDF: Learning to Forecast in the Frequency Domain

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Hao, Pan, Licheng, Chen, Zhichao, Yang, Degui, Zhang, Sen, Yang, Yifei, Liu, Xinggao, Li, Haoxuan, Tao, Dacheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909601773912064
author Wang, Hao
Pan, Licheng
Chen, Zhichao
Yang, Degui
Zhang, Sen
Yang, Yifei
Liu, Xinggao
Li, Haoxuan
Tao, Dacheng
author_facet Wang, Hao
Pan, Licheng
Chen, Zhichao
Yang, Degui
Zhang, Sen
Yang, Yifei
Liu, Xinggao
Li, Haoxuan
Tao, Dacheng
contents Time series modeling presents unique challenges due to autocorrelation in both historical data and future sequences. While current research predominantly addresses autocorrelation within historical data, the correlations among future labels are often overlooked. Specifically, modern forecasting models primarily adhere to the Direct Forecast (DF) paradigm, generating multi-step forecasts independently and disregarding label autocorrelation over time. In this work, we demonstrate that the learning objective of DF is biased in the presence of label autocorrelation. To address this issue, we propose the Frequency-enhanced Direct Forecast (FreDF), which mitigates label autocorrelation by learning to forecast in the frequency domain, thereby reducing estimation bias. Our experiments show that FreDF significantly outperforms existing state-of-the-art methods and is compatible with a variety of forecast models. Code is available at https://github.com/Master-PLC/FreDF.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02399
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FreDF: Learning to Forecast in the Frequency Domain
Wang, Hao
Pan, Licheng
Chen, Zhichao
Yang, Degui
Zhang, Sen
Yang, Yifei
Liu, Xinggao
Li, Haoxuan
Tao, Dacheng
Machine Learning
Artificial Intelligence
Applications
Time series modeling presents unique challenges due to autocorrelation in both historical data and future sequences. While current research predominantly addresses autocorrelation within historical data, the correlations among future labels are often overlooked. Specifically, modern forecasting models primarily adhere to the Direct Forecast (DF) paradigm, generating multi-step forecasts independently and disregarding label autocorrelation over time. In this work, we demonstrate that the learning objective of DF is biased in the presence of label autocorrelation. To address this issue, we propose the Frequency-enhanced Direct Forecast (FreDF), which mitigates label autocorrelation by learning to forecast in the frequency domain, thereby reducing estimation bias. Our experiments show that FreDF significantly outperforms existing state-of-the-art methods and is compatible with a variety of forecast models. Code is available at https://github.com/Master-PLC/FreDF.
title FreDF: Learning to Forecast in the Frequency Domain
topic Machine Learning
Artificial Intelligence
Applications
url https://arxiv.org/abs/2402.02399