A Lightweight Sparse Interaction Network for Time Series Forecasting

TL;DR

This paper introduces LSINet, a lightweight linear model with explicit sparse temporal interaction mechanisms, outperforming transformer and linear models in long-term time series forecasting in accuracy and efficiency.

Contribution

The paper proposes LSINet with MSIM and SIL, novel mechanisms for explicit sparse temporal interaction, improving long-term TSF performance over existing models.

Findings

LSINet outperforms transformer models in accuracy.

LSINet demonstrates higher efficiency in TSF tasks.

The proposed mechanisms effectively capture complex temporal dependencies.

Abstract

Recent work shows that linear models can outperform several transformer models in long-term time-series forecasting (TSF). However, instead of explicitly performing temporal interaction through self-attention, linear models implicitly perform it based on stacked MLP structures, which may be insufficient in capturing the complex temporal dependencies and their performance still has potential for improvement. To this end, we propose a Lightweight Sparse Interaction Network (LSINet) for TSF task. Inspired by the sparsity of self-attention, we propose a Multihead Sparse Interaction Mechanism (MSIM). Different from self-attention, MSIM learns the important connections between time steps through sparsity-induced Bernoulli distribution to capture temporal dependencies for TSF. The sparsity is ensured by the proposed self-adaptive regularization loss. Moreover, we observe the shareability of temporal interactions and propose to perform Shared Interaction Learning (SIL) for MSIM to further enhance efficiency and improve convergence. LSINet is a linear model comprising only MLP structures with low overhead and equipped with explicit temporal interaction mechanisms. Extensive experiments on public datasets show that LSINet achieves both higher accuracy and better efficiency than advanced linear models and transformer models in TSF tasks. The code is available at the link https://github.com/Meteor-Stars/LSINet.