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. 

University of Notre Dame

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.

Graph Readout Operation

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

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.

Learn Before

Related