FilterNet: Harnessing Frequency Filters for Time Series Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Kun, Fei, Jingru, Zhang, Qi, He, Hui, Hao, Shufeng, Lian, Defu, Fan, Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910684982280192
author Yi, Kun
Fei, Jingru
Zhang, Qi
He, Hui
Hao, Shufeng
Lian, Defu
Fan, Wei
author_facet Yi, Kun
Fei, Jingru
Zhang, Qi
He, Hui
Hao, Shufeng
Lian, Defu
Fan, Wei
contents While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting. However, forecasters based on Transformers are still suffering from vulnerability to high-frequency signals, efficiency in computation, and bottleneck in full-spectrum utilization, which essentially are the cornerstones for accurately predicting time series with thousands of points. In this paper, we explore a novel perspective of enlightening signal processing for deep time series forecasting. Inspired by the filtering process, we introduce one simple yet effective network, namely FilterNet, built upon our proposed learnable frequency filters to extract key informative temporal patterns by selectively passing or attenuating certain components of time series signals. Concretely, we propose two kinds of learnable filters in the FilterNet: (i) Plain shaping filter, that adopts a universal frequency kernel for signal filtering and temporal modeling; (ii) Contextual shaping filter, that utilizes filtered frequencies examined in terms of its compatibility with input signals for dependency learning. Equipped with the two filters, FilterNet can approximately surrogate the linear and attention mappings widely adopted in time series literature, while enjoying superb abilities in handling high-frequency noises and utilizing the whole frequency spectrum that is beneficial for forecasting. Finally, we conduct extensive experiments on eight time series forecasting benchmarks, and experimental results have demonstrated our superior performance in terms of both effectiveness and efficiency compared with state-of-the-art methods. Code is available at this repository: https://github.com/aikunyi/FilterNet
format Preprint
id arxiv_https___arxiv_org_abs_2411_01623
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FilterNet: Harnessing Frequency Filters for Time Series Forecasting
Yi, Kun
Fei, Jingru
Zhang, Qi
He, Hui
Hao, Shufeng
Lian, Defu
Fan, Wei
Machine Learning
Artificial Intelligence
Signal Processing
While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting. However, forecasters based on Transformers are still suffering from vulnerability to high-frequency signals, efficiency in computation, and bottleneck in full-spectrum utilization, which essentially are the cornerstones for accurately predicting time series with thousands of points. In this paper, we explore a novel perspective of enlightening signal processing for deep time series forecasting. Inspired by the filtering process, we introduce one simple yet effective network, namely FilterNet, built upon our proposed learnable frequency filters to extract key informative temporal patterns by selectively passing or attenuating certain components of time series signals. Concretely, we propose two kinds of learnable filters in the FilterNet: (i) Plain shaping filter, that adopts a universal frequency kernel for signal filtering and temporal modeling; (ii) Contextual shaping filter, that utilizes filtered frequencies examined in terms of its compatibility with input signals for dependency learning. Equipped with the two filters, FilterNet can approximately surrogate the linear and attention mappings widely adopted in time series literature, while enjoying superb abilities in handling high-frequency noises and utilizing the whole frequency spectrum that is beneficial for forecasting. Finally, we conduct extensive experiments on eight time series forecasting benchmarks, and experimental results have demonstrated our superior performance in terms of both effectiveness and efficiency compared with state-of-the-art methods. Code is available at this repository: https://github.com/aikunyi/FilterNet
title FilterNet: Harnessing Frequency Filters for Time Series Forecasting
topic Machine Learning
Artificial Intelligence
Signal Processing
url https://arxiv.org/abs/2411.01623