Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs

TL;DR

This paper introduces a novel graph-preserving grid layout (GPGL) that projects graphs onto regular grids, enabling CNNs to be effectively used for graph classification by bridging the gap between GCNs and CNNs.

Contribution

The paper proposes a principled, optimization-based grid layout method (GPGL) that preserves graph topology and facilitates CNN application to graph data, with improved data augmentation capabilities.

Findings

GPGL effectively preserves graph topology on grids.

The method improves graph classification accuracy.

Data augmentation is facilitated through multiple grid layouts.

Abstract

Graph convolutional networks (GCNs) suffer from the irregularity of graphs, while more widely-used convolutional neural networks (CNNs) benefit from regular grids. To bridge the gap between GCN and CNN, in contrast to previous works on generalizing the basic operations in CNNs to graph data, in this paper we address the problem of how to project undirected graphs onto the grid in a {\em principled} way where CNNs can be used as backbone for geometric deep learning. To this end, inspired by the literature of graph drawing we propose a novel graph-preserving grid layout (GPGL), an integer programming that minimizes the topological loss on the grid. Technically we propose solving GPGL approximately using a {\em regularized} Kamada-Kawai algorithm, a well-known nonconvex optimization technique in graph drawing, with a vertex separation penalty that improves the rounding performance on top of the solutions from relaxation. Using GPGL we can easily conduct data augmentation as every local minimum will lead to a grid layout for the same graph. Together with the help of multi-scale maxout CNNs, we demonstrate the empirical success of our method for graph classification.