Spatio-Temporal Graph Neural Networks: A Survey
This is a survey paper, providing an overview for researchers and practitioners interested in STGNNs, but it is incremental as it summarizes existing work without introducing new methods.
The paper addresses the limitation of Graph Neural Networks (GNNs) in handling time-varying data by surveying Spatio-Temporal Graph Neural Networks (STGNNs), which extend GNNs to incorporate temporal factors and have achieved superior performance in time-dependent applications.
Graph Neural Networks have gained huge interest in the past few years. These powerful algorithms expanded deep learning models to non-Euclidean space and were able to achieve state of art performance in various applications including recommender systems and social networks. However, this performance is based on static graph structures assumption which limits the Graph Neural Networks performance when the data varies with time. Spatiotemporal Graph Neural Networks are extension of Graph Neural Networks that takes the time factor into account. Recently, various Spatiotemporal Graph Neural Network algorithms were proposed and achieved superior performance compared to other deep learning algorithms in several time dependent applications. This survey discusses interesting topics related to Spatiotemporal Graph Neural Networks, including algorithms, applications, and open challenges.