Comment:
Published in ArXiv 2019
This is a introduction paper that helps to understand latest progress and also provide github repos for different implementations.
Code: See last page (22)
Contribution:
We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes and benchmarks of the existing algorithms on different learning tasks.
Recurrent graph neural networks (RecGNNs) mostly are pioneer works of graph neural networks. RecGNNs aim to learn node representations with recurrent neural architectures
Convolutional graph neural networks (ConvGNNs) generalize the operation of convolution from grid data to graph data.ConvGNNs play a central role in building up many other complex GNN models.
Graph autoencoders (GAEs) are unsupervised learning frameworks which encode nodes/graphs into a latent vector space and reconstruct graph data from the encoded information. GAEs are used to learn network embeddings and graph generative distributions.
Spatial-temporal graph neural networks (STGNNs) aim to learn hidden patterns from spatial-temporal graphs, which become increasingly important in a variety of applications such as traffic speed forecasting [72], driver maneuver anticipation [73], and human action recognition [75].
Link: SemanticScholar
Comment: Published in ArXiv 2019 This is a introduction paper that helps to understand latest progress and also provide github repos for different implementations. Code: See last page (22)
Contribution: We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes and benchmarks of the existing algorithms on different learning tasks. Recurrent graph neural networks (RecGNNs) mostly are pioneer works of graph neural networks. RecGNNs aim to learn node representations with recurrent neural architectures Convolutional graph neural networks (ConvGNNs) generalize the operation of convolution from grid data to graph data.ConvGNNs play a central role in building up many other complex GNN models. Graph autoencoders (GAEs) are unsupervised learning frameworks which encode nodes/graphs into a latent vector space and reconstruct graph data from the encoded information. GAEs are used to learn network embeddings and graph generative distributions. Spatial-temporal graph neural networks (STGNNs) aim to learn hidden patterns from spatial-temporal graphs, which become increasingly important in a variety of applications such as traffic speed forecasting [72], driver maneuver anticipation [73], and human action recognition [75].