WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Jiecheng, Han, Xu, Sun, Yan, Yang, Shihao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908813706133504
author Lu, Jiecheng
Han, Xu
Sun, Yan
Yang, Shihao
author_facet Lu, Jiecheng
Han, Xu
Sun, Yan
Yang, Shihao
contents We propose a Weighted Autoregressive Varying gatE (WAVE) attention mechanism equipped with both Autoregressive (AR) and Moving-average (MA) components. It can adapt to various attention mechanisms, enhancing and decoupling their ability to capture long-range and local temporal patterns in time series data. In this paper, we first demonstrate that, for the time series forecasting (TSF) task, the previously overlooked decoder-only autoregressive Transformer model can achieve results comparable to the best baselines when appropriate tokenization and training methods are applied. Moreover, inspired by the ARMA model from statistics and recent advances in linear attention, we introduce the full ARMA structure into existing autoregressive attention mechanisms. By using an indirect MA weight generation method, we incorporate the MA term while maintaining the time complexity and parameter size of the underlying efficient attention models. We further explore how indirect parameter generation can produce implicit MA weights that align with the modeling requirements for local temporal impacts. Experimental results show that WAVE attention that incorporates the ARMA structure consistently improves the performance of various AR attentions on TSF tasks, achieving state-of-the-art results.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03159
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting
Lu, Jiecheng
Han, Xu
Sun, Yan
Yang, Shihao
Machine Learning
Artificial Intelligence
We propose a Weighted Autoregressive Varying gatE (WAVE) attention mechanism equipped with both Autoregressive (AR) and Moving-average (MA) components. It can adapt to various attention mechanisms, enhancing and decoupling their ability to capture long-range and local temporal patterns in time series data. In this paper, we first demonstrate that, for the time series forecasting (TSF) task, the previously overlooked decoder-only autoregressive Transformer model can achieve results comparable to the best baselines when appropriate tokenization and training methods are applied. Moreover, inspired by the ARMA model from statistics and recent advances in linear attention, we introduce the full ARMA structure into existing autoregressive attention mechanisms. By using an indirect MA weight generation method, we incorporate the MA term while maintaining the time complexity and parameter size of the underlying efficient attention models. We further explore how indirect parameter generation can produce implicit MA weights that align with the modeling requirements for local temporal impacts. Experimental results show that WAVE attention that incorporates the ARMA structure consistently improves the performance of various AR attentions on TSF tasks, achieving state-of-the-art results.
title WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.03159