Boosting MLPs with a Coarsening Strategy for Long-Term Time Series Forecasting
This work addresses computational efficiency and accuracy challenges in time series forecasting for domains like finance or weather, but it is incremental as it builds on existing MLP-based methods with a novel coarsening strategy.
The paper tackles the problem of balancing expressive power and computational efficiency in long-term time series forecasting by proposing CP-Net, a method that uses a coarsening strategy with MLPs to improve contextual dependencies and information flow, resulting in a 4.1% improvement over the state-of-the-art on seven benchmarks.
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.