Multi-Scale Spatial-Temporal Transformer: A Novel Framework for Spatial-Temporal Edge Data Prediction

Spatial-temporal prediction is an important part of a great number of applications, such as urban traffic control, urban traffic management, and urban traffic planning. However, real-world spatial-temporal data often have complex patterns, so it is still challenging to predict them accurately. Most existing spatial-temporal prediction models fail to aggregate the spatial features in a suitable neighborhood during fixed spatial dependencies extraction and lack adequately comprehensive time series analysis for intricate temporal dependencies. This paper proposes a novel model named multi-scale spatial-temporal transformer network (MSSTTN) to deal with intricate spatial-temporal patterns. Firstly, we develop an improved graph wavelet neural network, which learns how to pass the spatial graph signals of different frequency scales to adjust the neighborhood of feature aggregation adaptively. Then, we propose decomposing the time series into local trend-cyclical parts of various scales during time series analysis, making the model capture more reliable temporal dependencies. The proposed model has been evaluated on publicly available real-world datasets. The experimental findings indicate that the proposed model exhibits superior performance compared to conventional techniques including, spatial-temporal transformer (STTNs), GraphWaveNet, and others.

Automated summary

Spatial-temporal prediction is crucial for various applications, such as urban traffic control, management, and planning. However, predicting real-world spatial-temporal data accurately is still challenging due to their complex patterns. Most existing models lack effective aggregation of spatial features and comprehensive time series analysis for intricate dependencies. This paper proposes a novel multi-scale spatial-temporal transformer network (MSSTTN) that addresses these issues and outperforms conventional techniques in publicly available datasets.