Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks in Molecular Graph Analysis

Katsuhiko Ishiguro, Shin-ichi Maeda, Masanori Koyama

Keywords: Graph Neural Networks, molecular graph analysis, supernode, auxiliary module

TL;DR: Proposing an auxiliary module with its own I/O that can be attached to a generic GNN of message passing type in order to improve its representation power/ generalization performance on small-graph datasets.

Abstract:

Graph Neural Network (GNN) is a popular architecture for the analysis of chemical molecules, and it has numerous applications in material and medicinal science.
Current lines of GNNs developed for molecular analysis, however, do not fit well on the training set, and their performance does not scale well with the complexity of the network.
In this paper, we propose an auxiliary module to be attached to a GNN that can boost the representation power of the model without hindering the original GNN architecture.
Our auxiliary module can improve the representation power and the generalization ability of a wide variety of GNNs, including those that are used commonly in biochemical applications.