search

benedekrozemberczki / ClusterGCN

A PyTorch implementation of "Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks" (KDD 2019).
GNU General Public License v3.0
786 stars 135 forks source link

Different partition size #3

Closed tanwimallick closed 5 years ago

tanwimallick commented 5 years ago

Metis may provide sub-graphs with unequal number of nodes. The size of the adjacency matrix will be different. How do you handle this issue during training?

benedekrozemberczki commented 5 years ago

The loss is averaged on the partitions.