Multi-View Attribute Graph Convolution Networks for Clustering

Graph neural networks (GNNs) have made considerable achievements in processing graph-structured data. However, existing methods cannot allocate learnable weights to different nodes in the neighborhood and lack of robustness on account of neglecting both node attributes and graph reconstruction. Moreover, most of multi-view GNNs mainly focus on the case of multiple graphs, while designing GNNs for solving graph-structured data of multi-view attributes is still under-explored. In this paper, we propose a novel Multi-View Attribute Graph Convolution Networks (MAGCN) model for the clustering task. MAGCN is designed with two-pathway encoders that map graph embedding features and learn view-consistency information. Specifically, the first pathway develops multiview attribute graph attention networks to reduce the noise/redundancy and learn the graph embedding features of multi-view graph data. The second pathway develops consistent embedding encoders to capture the geometric relationship and the consistency of probability distribution among different views, which adaptively finds a consistent clustering embedding space for multi-view attributes. Experiments on three benchmark graph databases show the effectiveness of our method compared with several state-of-the-art algorithms.

[1]  Fei Wang,et al.  Multi-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson's Disease , 2018, AMIA.

[2]  Xinbo Gao,et al.  Multiview Clustering by Joint Latent Representation and Similarity Learning , 2020, IEEE Transactions on Cybernetics.

[3]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[4]  Wei Lu,et al.  Deep Neural Networks for Learning Graph Representations , 2016, AAAI.

[5]  Lina Yao,et al.  Adversarially Regularized Graph Autoencoder , 2018, IJCAI.

[6]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[7]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[8]  Jing Jiang,et al.  Attributed Graph Clustering: A Deep Attentional Embedding Approach , 2019, IJCAI.

[9]  Yun Fu,et al.  Partial Multi-view Clustering via Consistent GAN , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[10]  Chun Wang,et al.  MGAE: Marginalized Graph Autoencoder for Graph Clustering , 2017, CIKM.

[11]  J. Neyman,et al.  Mathematical Statistics and Probability , 1962 .

[12]  Jian Pei,et al.  Community Preserving Network Embedding , 2017, AAAI.

[13]  Enhong Chen,et al.  Learning Deep Representations for Graph Clustering , 2014, AAAI.

[14]  Joshua E. Blumenstock,et al.  Multi-GCN: Graph Convolutional Networks for Multi-View Networks, with Applications to Global Poverty , 2019, AAAI.

[15]  Zhaoyang Li,et al.  Deep Adversarial Multiview Clustering Network , 2019 .

[16]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[17]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[18]  Ying Liang,et al.  Multi-view projected clustering with graph learning , 2020, Neural Networks.

[19]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[20]  Fei Wang,et al.  Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders , 2018, IJCAI.

[21]  Max Welling,et al.  Variational Graph Auto-Encoders , 2016, ArXiv.

[22]  Jieping Ye,et al.  Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting , 2019, AAAI.

[23]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.