论文笔记：A Comprehensive Survey on Graph Neural Networks

GNN的发展

• Spectral graph theory: The first prominent research on GCNs is presented in Bruna et al. (2013), which develops a variant of graph convolution based on spectral graph theory
  • Since that time, there have been increasing improvements, extensions, and approximations on spectral-based graph convolutional networks
• Spatial-based graph convolutional networks: As spectral methods usually handle the whole graph simultaneously and are difficult to parallel or scale to large graphs, spatial-based graph convolutional networks have rapidly developed recently
  • Together with sampling strategies, the computation can be performed in a batch of nodes instead of the whole graph [24], [27], which has the potential to improve the efficiency.
• Others: In addition to graph convolutional networks, many alternative graph neural networks have been developed in the past few years.
  • These approaches include graph attention networks, graph autoencoders, graph generative networks, and graph spatial-temporal networks.

GNN vs Network embedding

• 两者属于相交的关系，交集是Deep learning
• Network embedding aims to represent network vertices into a low-dimensional vector space, by preserving both network topology structure and node content information, so that any subsequent graph analytics tasks such as classification, clustering, and recommendation can be easily performed by using simple off-the-shelf learning machine algorithm
• Many network embedding algorithms are typically unsupervised algorithms and they can be broadly classified into three groups [32]
  • matrix factorization [38], [39]
  • random walks [40]
  • deep learning approaches
• The deep learning approaches for network embedding at the same time belong to graph neural networks, which include graph autoencoder-based algorithms (e.g., DNGR [41] and SDNE [42]) and graph convolution neural networks with unsupervised training(e.g., GraphSage [24]).
• 

GNN分类，5类