This is a basic type of readout operation, it uses simple statistics such as summation, averaging, max-pooling to aggregate nodes representation to graph representation. 

Statistics Type of Readout Operation

Some graphs have rich hierarchy structure. For this type of graph, we can use hierarchical clustering methods.

Hierarchical Clustering Type of Readout Operation

This method imposes a node order on the graph, and then use 1-D pooling as Convolutional Neural Network to aggregate node representation.

Readout by Imposing Orders

When a graph-level representation is needed to tackle graph-level tasks, node-level representations can be aggregated into a single graph-level representation. This aggregation process is referred to as a readout operation.

University of Notre Dame

Google

GCN uses convolution operation and readout operation to grasp node level and graph level patterns.

Graph Convolutional Networks (GCN)

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

Convolution operations can be divided into two types:

1)	Spectral convolution

2)	Spatial convolution

3)	Mixture of spectral convolution and special convolution


Types of Convolution Operation

1)	Attention Mechanism

2)	Residual and Jumping Connections

3)	Utilizing Edge Features

4)	Sampling Methods

5)	Inductive Setting

6)	Theoretical Analysis


Learn Before

Related

Learn After