Motif-based Graph Representation Learning with Application to Chemical Molecules

1 code implementation • 9 Aug 2022 • Yifei Wang, Shiyang Chen, Guobin Chen, Ethan Shurberg, Hang Liu, Pengyu Hong

MCM builds a motif vocabulary in an unsupervised way and deploys a novel motif convolution operation to extract the local structural context of individual nodes, which is then used to learn higher-level node representations via multilayer perceptron and/or message passing in graph neural networks.

Graph Learning Graph Representation Learning