MCformer: Multivariate Time Series Forecasting with Mixed-Channels Transformer

TL;DR

MCformer introduces a novel mixed channels strategy for multivariate time-series forecasting, combining the benefits of channel independence and dependence to improve long-term feature modeling and outperform existing methods.

Contribution

The paper proposes the Mixed Channels strategy and MCformer model, which effectively captures inter-channel correlations while maintaining generalization in multivariate forecasting.

Findings

Outperforms pure CI strategy in experiments

Effectively captures inter-channel correlations

Enhances long-term feature modeling

Abstract

The massive generation of time-series data by largescale Internet of Things (IoT) devices necessitates the exploration of more effective models for multivariate time-series forecasting. In previous models, there was a predominant use of the Channel Dependence (CD) strategy (where each channel represents a univariate sequence). Current state-of-the-art (SOTA) models primarily rely on the Channel Independence (CI) strategy. The CI strategy treats all channels as a single channel, expanding the dataset to improve generalization performance and avoiding inter-channel correlation that disrupts long-term features. However, the CI strategy faces the challenge of interchannel correlation forgetting. To address this issue, we propose an innovative Mixed Channels strategy, combining the data expansion advantages of the CI strategy with the ability to counteract inter-channel correlation forgetting. Based on this strategy, we introduce MCformer, a multivariate time-series forecasting model with mixed channel features. The model blends a specific number of channels, leveraging an attention mechanism to effectively capture inter-channel correlation information when modeling long-term features. Experimental results demonstrate that the Mixed Channels strategy outperforms pure CI strategy in multivariate time-series forecasting tasks.