Graphs are useful data structures in complex real-life applications such as modeling physical systems, learning molecular fingerprints, controlling traffic networks, and recommending friends in social networks. However, these tasks require dealing with non-Euclidean graph data that contains rich relational information between elements and cannot be well handled by traditional deep learning models (e.g., convolutional neural networks (CNNs) or recurrent neural networks (RNNs)). Nodes in graphs usually contain useful feature information that cannot be well addressed in most unsupervised representation learning methods (e.g., network embedding methods). Graph neural networks (GNNs) are proposed to combine the feature information and the graph structure to learn better representations on graphs via feature propagation and aggregation. Due to its convincing performance and high interpretability, GNN has recently become a widely applied graph analysis tool.

STGCN图卷积神经网络

图卷积神经网络从入门到实战

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. 图卷积神经网络，2018年AAAI论文代码。

图卷积神经网络(GCNNs)是深度学习技术在图结构数据问题上的一种强大的扩展。我们对GCNNs的几种池方法进行了实证评估，并将这些图池化方法与三种不同架构(GCN、TAGCN和GraphSAGE)进行了组合。我们证实，图池化，特别是DiffPool，提高了流行的图分类数据集的分类精度，并发现，平均而言，TAGCN达到了可比或更好的精度比GCN和GraphSAGE，特别是对数据集较大和稀疏的图结构。

resources for graph convolutional networks （图卷积神经网络相关资源）

过去几年,卷积神经网络因其强大的建模能力引起广泛关注,在自然语言处理、图像识别等领域成功应用。然而,传统的卷积神经网络只能处理欧氏空间数据,而现实生活中的许多场景,如交通网络、社交网络、引用网络等,都是以图数据的形式存在。

Graph Neural Networks A Review of Methods and Applications