Gated Graph Sequence Neural Networks (GGS-NNs) made notable improvements to this type of neural network. It replaced the aggregation unit with Gated Recurrent Unit,  which is a model structure commonly used in RNN models, to promote information propagation.

Improvement of Node Level Graph RNN 

Under node level graph RNN, each node is represented as a lower dimension vector, and the vector for each node is an aggregation of vectors of its neighbor node. And this aggregation is repeated multiple times to encode graph structure information in node representation. 

University of Notre Dame

RNN is a class of neural network models that model sequential data. Examples include Gated Recurrent Units (GRU) or Long Short-Term Memory (LSTM) model. RNN can be adapted to graph modeling with some moderate modification.

Graph Recurrent Neural Networks (RNN)

Zhang, Z., Cui, P., & Zhu, W. (2020). Deep learning on graphs: A survey. IEEE Transactions on Knowledge and Data Engineering.

Deep Learning on Graphs: A Survey

Node Level Graph RNN

Graph level RNN use RNN to capture graph level pattern, such as temporal pattern of dynamic graph and sequential pattern under different graph granularities. 

An example under this category is Dynamic Graph Neural Network (DGNN). DGNN can capture the temporal pattern of a dynamic graph. When a new edge is added to the graph, it uses LSTM to update the two newly connected nodes and their immediate neighbors.

Learn Before

Related

Learn After