MarkovGNN: Graph Neural Networks on Markov Diffusion
This addresses the challenge of modeling dynamic community structures in graph neural networks for researchers and practitioners in network analysis, though it appears incremental as it builds on existing GNNs.
The paper tackles the problem of learning from networks with community structures by developing MarkovGNN, which captures community formation and evolution in different convolutional layers using a Markov process, and it outperforms other GNNs on clustering, node classification, and visualization tasks.
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}.