CGN: A Simple Yet Effective Multi-Channel Gated Network for Long-Term Time Series Forecasting

Abstract

Transformers have gained widespread attention in the field of time series forecasting due to their exceptional capability to capture intricate interactions within sequences. However, as the sequence length increases, Transformer-based models face disadvantages such as high memory consumption, blurred long-range dependency, and susceptibility to overfitting. To address this, we introduce CGN, a lightweight multi-channel gated network. CGN employs a channel gate to identify and filter out noisy inputs, focusing on the most relevant variables. Unlike traditional Transformer-based models, our model is exceptionally lightweight, making it suitable for tasks requiring a longer historical window to enhance the accuracy of long-term forecasting. Experimental results demonstrate that our model outperforms the state-of-the-art Transformer-based and MLP-based models across six real-world LTSF benchmarks. Specifically, CGN surpasses the latest strongest Patch-Transformer in 90% cases with a significant reduction in the average number of trainable parameters, maximum memory consumption, running time, and inference time.