Community detection is an important application of GNNs. In the paper "Supervised Community Detection with Line Graph Neural Networks", published at ICLR 2019, LGNN is proposed. LGNN operates simultaneouly on both the original graph and its line graph. In the paper "Graph Convolutional Networks Meet Markov Random Fields: Semi-Supervised Community Detection in Attribute Networks", published at AAAI 2019, MRFasGCN is proposed. MRFasGCN is an end-to-end deep learning method to integrate GCN and MRF. Both of them achieve success in synthetic and real-world datasets and have not implemented by PyG.
Community detection is an important application of GNNs. In the paper "Supervised Community Detection with Line Graph Neural Networks", published at ICLR 2019, LGNN is proposed. LGNN operates simultaneouly on both the original graph and its line graph. In the paper "Graph Convolutional Networks Meet Markov Random Fields: Semi-Supervised Community Detection in Attribute Networks", published at AAAI 2019, MRFasGCN is proposed. MRFasGCN is an end-to-end deep learning method to integrate GCN and MRF. Both of them achieve success in synthetic and real-world datasets and have not implemented by PyG.