CommunityGAN: Community Detection with Generative Adversarial Nets

20 Jan 2019  ยท  Yuting Jia, Qinqin Zhang, Wei-Nan Zhang, Xinbing Wang ยท

Community detection refers to the task of discovering groups of vertices sharing similar properties or functions so as to understand the network data. With the recent development of deep learning, graph representation learning techniques are also utilized for community detection. However, the communities can only be inferred by applying clustering algorithms based on learned vertex embeddings. These general cluster algorithms like K-means and Gaussian Mixture Model cannot output much overlapped communities, which have been proved to be very common in many real-world networks. In this paper, we propose CommunityGAN, a novel community detection framework that jointly solves overlapping community detection and graph representation learning. First, unlike the embedding of conventional graph representation learning algorithms where the vector entry values have no specific meanings, the embedding of CommunityGAN indicates the membership strength of vertices to communities. Second, a specifically designed Generative Adversarial Net (GAN) is adopted to optimize such embedding. Through the minimax competition between the motif-level generator and discriminator, both of them can alternatively and iteratively boost their performance and finally output a better community structure. Extensive experiments on synthetic data and real-world tasks demonstrate that CommunityGAN achieves substantial community detection performance gains over the state-of-the-art methods.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Community Detection Amazon CommunityGAN F1-score 0.091 # 1
Clique Prediction arXiv-AstroPh 2-clique CommunityGAN AUC 92.3 # 1
Clique Prediction arXiv-AstroPh 3-clique CommunityGAN AUC 99 # 1
Clique Prediction arXiv-AstroPh 4-clique CommunityGAN AUC 97 # 1
Clique Prediction arXiv-GrQc 2-clique CommunityGAN AUC 90.4 # 1
Clique Prediction arXiv-GrQc 3-clique CommunityGAN AUC 99.3 # 1
Clique Prediction arXiv-GrQc 4-clique CommunityGAN AUC 95.6 # 1
Community Detection DBLP CommunityGAN F1-Score 0.153 # 1

Methods


No methods listed for this paper. Add relevant methods here