MxPool: Multiplex Pooling for Hierarchical Graph Representation Learning

TL;DR

MxPool introduces a multiplex pooling approach that employs multiple graph neural networks to better handle diverse graph properties, improving classification performance across various benchmarks.

Contribution

The paper proposes MxPool, a novel multiplex pooling method that leverages multiple GNNs and graph properties for enhanced hierarchical graph representation learning.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Effectively handles diverse graph sizes and properties.

Demonstrates superior classification accuracy.

Abstract

How to utilize deep learning methods for graph classification tasks has attracted considerable research attention in the past few years. Regarding graph classification tasks, the graphs to be classified may have various graph sizes (i.e., different number of nodes and edges) and have various graph properties (e.g., average node degree, diameter, and clustering coefficient). The diverse property of graphs has imposed significant challenges on existing graph learning techniques since diverse graphs have different best-fit hyperparameters. It is difficult to learn graph features from a set of diverse graphs by a unified graph neural network. This motivates us to use a multiplex structure in a diverse way and utilize a priori properties of graphs to guide the learning. In this paper, we propose MxPool, which concurrently uses multiple graph convolution/pooling networks to build a hierarchical learning structure for graph representation learning tasks. Our experiments on numerous graph classification benchmarks show that our MxPool has superiority over other state-of-the-art graph representation learning methods.