MDMLP-EIA: Multi-domain Dynamic MLPs with Energy Invariant Attention for Time Series Forecasting

TL;DR

This paper introduces MDMLP-EIA, a novel multi-domain dynamic MLP model with energy invariant attention, improving time series forecasting by effectively capturing weak signals, enhancing robustness, and adjusting capacity dynamically.

Contribution

The paper proposes three innovations: an adaptive dual-domain seasonal MLP, an energy invariant attention mechanism, and a dynamic capacity adjustment for MLPs, advancing time series forecasting methods.

Findings

Achieves state-of-the-art accuracy on nine benchmark datasets.

Demonstrates improved robustness against disturbances.

Offers better computational efficiency than existing models.

Abstract

Time series forecasting is essential across diverse domains. While MLP-based methods have gained attention for achieving Transformer-comparable performance with fewer parameters and better robustness, they face critical limitations including loss of weak seasonal signals, capacity constraints in weight-sharing MLPs, and insufficient channel fusion in channel-independent strategies. To address these challenges, we propose MDMLP-EIA (Multi-domain Dynamic MLPs with Energy Invariant Attention) with three key innovations. First, we develop an adaptive fused dual-domain seasonal MLP that categorizes seasonal signals into strong and weak components. It employs an adaptive zero-initialized channel fusion strategy to minimize noise interference while effectively integrating predictions. Second, we introduce an energy invariant attention mechanism that adaptively focuses on different feature channels within trend and seasonal predictions across time steps. This mechanism maintains constant total signal energy to align with the decomposition-prediction-reconstruction framework and enhance robustness against disturbances. Third, we propose a dynamic capacity adjustment mechanism for channel-independent MLPs. This mechanism scales neuron count with the square root of channel count, ensuring sufficient capacity as channels increase. Extensive experiments across nine benchmark datasets demonstrate that MDMLP-EIA achieves state-of-the-art performance in both prediction accuracy and computational efficiency.