Random Projection Layers for Multidimensional Time Series Forecasting
arxiv(2024)
摘要
All-Multi-Layer Perceptron (all-MLP) mixer models have been shown to be
effective for time series forecasting problems. However, when such a model is
applied to high-dimensional time series (e.g., the time series in a
spatial-temporal dataset), its performance is likely to degrade due to
overfitting issues. In this paper, we propose an all-MLP time series
forecasting architecture, referred to as RPMixer. Our method leverages the
ensemble-like behavior of deep neural networks, where each individual block
within the network acts like a base learner in an ensemble model, especially
when identity mapping residual connections are incorporated. By integrating
random projection layers into our model, we increase the diversity among the
blocks' outputs, thereby enhancing the overall performance of RPMixer.
Extensive experiments conducted on large-scale spatial-temporal forecasting
benchmark datasets demonstrate that our proposed method outperforms alternative
methods, including both spatial-temporal graph models and general forecasting
models.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要