A Multi-scale Representation Learning Framework for Long-Term Time Series Forecasting

TL;DR

This paper introduces a multi-scale, channel-aware MLP framework for long-term time series forecasting, effectively modeling complex temporal dynamics and outperforming recent methods in accuracy and efficiency.

Contribution

It presents a novel multi-scale, channel-sensitive MLP-based framework that disentangles trend and seasonal components for improved long-term forecasting.

Findings

MDMixer improves MAE by 4.64% over TimeMixer

Balances training efficiency and interpretability

Effective multi-scale and channel-specific modeling

Abstract

Long-term time series forecasting (LTSF) offers broad utility in practical settings like energy consumption and weather prediction. Accurately predicting long-term changes, however, is demanding due to the intricate temporal patterns and inherent multi-scale variations within time series. This work confronts key issues in LTSF, including the suboptimal use of multi-granularity information, the neglect of channel-specific attributes, and the unique nature of trend and seasonal components, by introducing a proficient MLP-based forecasting framework. Our method adeptly disentangles complex temporal dynamics using clear, concurrent predictions across various scales. These multi-scale forecasts are then skillfully integrated through a system that dynamically assigns importance to information from different granularities, sensitive to individual channel characteristics. To manage the specific features of temporal patterns, a two-pronged structure is utilized to model trend and seasonal elements independently. Experimental results on eight LTSF benchmarks demonstrate that MDMixer improves average MAE performance by 4.64% compared to the recent state-of-the-art MLP-based method (TimeMixer), while achieving an effective balance between training efficiency and model interpretability.