论文标题
使用模块化设计及以后增强时空预测模型
Enhancing Spatiotemporal Prediction Model using Modular Design and Beyond
论文作者
论文摘要
预测学习使用已知状态在一段时间内产生未来状态。预测时空序列是一项具有挑战性的任务，因为时空序列在时间和空间上各不相同。主流方法是使用基于RNN或基于变压器的体系结构同时对空间和时间结构进行建模，然后通过在自动回归方式中使用学习的经验来生成未来数据。学习空间和时间特征的方法同时为模型带来了许多参数，这使得模型难以收敛。在本文中，提出了模块化设计，该设计将时空序列模型分解为两个模块：空间编码器解码器和一个预测指标。这两个模块可以提取空间特征并分别预测未来数据。空间编码器解码器将数据映射到潜在的嵌入空间中，并从潜在空间中生成数据，而预测器预测未来嵌入了过去。通过将设计应用于当前的KTH-ACTION和MOVITMNIST数据集的研究和执行实验，我们都可以提高计算性能并获得最新的结果。
Predictive learning uses a known state to generate a future state over a period of time. It is a challenging task to predict spatiotemporal sequence because the spatiotemporal sequence varies both in time and space. The mainstream method is to model spatial and temporal structures at the same time using RNN-based or transformer-based architecture, and then generates future data by using learned experience in the way of auto-regressive. The method of learning spatial and temporal features simultaneously brings a lot of parameters to the model, which makes the model difficult to be convergent. In this paper, a modular design is proposed, which decomposes spatiotemporal sequence model into two modules: a spatial encoder-decoder and a predictor. These two modules can extract spatial features and predict future data respectively. The spatial encoder-decoder maps the data into a latent embedding space and generates data from the latent space while the predictor forecasts future embedding from past. By applying the design to the current research and performing experiments on KTH-Action and MovingMNIST datasets, we both improve computational performance and obtain state-of-the-art results.
