Long Input Sequence Network for Long Time Series Forecasting

TL;DR

This paper introduces a novel neural network architecture that decouples multi-scale temporal patterns in long time series, enabling longer input handling, improved accuracy, and interpretability in forecasting tasks.

Contribution

The paper proposes a series-decomposition module and a multi-token pattern recognition network to effectively model multi-scale patterns and extend input length in time series forecasting.

Findings

Handles inputs up to 10 times longer

Achieves 38% maximum precision improvement

Offers low complexity and high interpretability

Abstract

Short fixed-length inputs are the main bottleneck of deep learning methods in long time-series forecasting tasks. Prolonging input length causes overfitting, rapidly deteriorating accuracy. Our research indicates that the overfitting is a combination reaction of the multi-scale pattern coupling in time series and the fixed focusing scale of current models. First, we find that the patterns exhibited by a time series across various scales are reflective of its multi-periodic nature, where each scale corresponds to specific period length. Second, We find that the token size predominantly dictates model behavior, as it determines the scale at which the model focuses and the context size it can accommodate. Our idea is to decouple the multi-scale temporal patterns of time series and to model each pattern with its corresponding period length as token size. We introduced a novel series-decomposition module(MPSD), and a Multi-Token Pattern Recognition neural network(MTPR), enabling the model to handle \textit{inputs up to $10\times$ longer}. Sufficient context enhances performance(\textit{38% maximum precision improvement}), and the decoupling approach offers \textit{Low complexity($0.22\times$ cost)} and \textit{high interpretability}.