MarkovGNN: Graph Neural Networks on Markov Diffusion

TL;DR

MarkovGNN introduces a novel approach for graph neural networks that models community formation and evolution using Markov processes, enhancing performance in clustering, classification, and visualization tasks.

Contribution

It presents a new Markov-based method integrated into GNNs to better capture community dynamics, applicable to various existing GNN architectures.

Findings

Outperforms existing GNNs in clustering tasks

Improves node classification accuracy

Enhances graph visualization quality

Abstract

Most real-world networks contain well-defined community structures where nodes are densely connected internally within communities. To learn from these networks, we develop MarkovGNN that captures the formation and evolution of communities directly in different convolutional layers. Unlike most Graph Neural Networks (GNNs) that consider a static graph at every layer, MarkovGNN generates different stochastic matrices using a Markov process and then uses these community-capturing matrices in different layers. MarkovGNN is a general approach that could be used with most existing GNNs. We experimentally show that MarkovGNN outperforms other GNNs for clustering, node classification, and visualization tasks. The source code of MarkovGNN is publicly available at \url{https://github.com/HipGraph/MarkovGNN}.