Boosting MLPs with a Coarsening Strategy for Long-Term Time Series Forecasting

TL;DR

This paper introduces CP-Net, a coarsening strategy-enhanced MLP model for long-term time series forecasting that improves accuracy and efficiency by capturing broader contextual information through information granules.

Contribution

The paper proposes the Coarsened Perceptron Network (CP-Net), a novel MLP-based architecture with a coarsening strategy and multi-scale fusion for better long-term forecasting.

Findings

Achieves 4.1% improvement over SOTA on seven benchmarks.

Maintains linear computational complexity and low runtime.

Effectively captures semantic and contextual patterns over larger timespans.

Abstract

Deep learning methods have been exerting their strengths in long-term time series forecasting. However, they often struggle to strike a balance between expressive power and computational efficiency. Resorting to multi-layer perceptrons (MLPs) provides a compromising solution, yet they suffer from two critical problems caused by the intrinsic point-wise mapping mode, in terms of deficient contextual dependencies and inadequate information bottleneck. Here, we propose the Coarsened Perceptron Network (CP-Net), featured by a coarsening strategy that alleviates the above problems associated with the prototype MLPs by forming information granules in place of solitary temporal points. The CP-Net utilizes primarily a two-stage framework for extracting semantic and contextual patterns, which preserves correlations over larger timespans and filters out volatile noises. This is further enhanced by a multi-scale setting, where patterns of diverse granularities are fused towards a comprehensive prediction. Based purely on convolutions of structural simplicity, CP-Net is able to maintain a linear computational complexity and low runtime, while demonstrates an improvement of 4.1% compared with the SOTA method on seven forecasting benchmarks.