Deep attributed graph clustering with self-separation regularization and parameter-free cluster estimation. (October 2021)

• Record Type: Journal Article
• Authors: Ji, Junzhong; Liang, Ye; Lei, Minglong
• Is Part Of: Neural networks. Volume 142(2021)
• Page Start: 522
• Page End: 533
• Publication Date: 2021-10
• Subjects: Attributed graph clustering -- Graph convolutional networks -- Parameter-free cluster estimation -- Self-separation regularization; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2021.07.012
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Detecting clusters over attributed graphs is a fundamental task in the graph analysis field. The goal is to partition nodes into dense clusters based on both their attributes and structures. Modern graph neural networks provide facilitation to jointly capture the above information in attributed graphs with a feature aggregation manner, and have achieved great success in attributed graph clustering. However, existing methods mainly focus on capturing the proximity information in graphs and often fail to learn cluster-friendly features during the training of models. Besides, similar to many deep clustering frameworks, current methods based on graph neural networks require a preassigned cluster number before estimating the clusters. To address these limitations, we propose in this paper a deep attributed clustering method based on self-separated graph neural networks and parameter-free cluster estimation. First, to learn cluster-friendly features, we jointly optimize a jumping graph convolutional auto-encoder with a self-separation regularizer, which learns clusters with changing sizes while keeping dense intra-cluster structures and sparse inter structures. Second, an additional softmax auto-encoder is trained to determine the natural cluster number from the data. The hidden units capture cluster structures and can be used to estimate the number of clusters. Extensive experiments show the effectiveness of the proposed model. Highlights: We propose a novel method to learn highly separated clusters without cluster number. The jumping GCN is used to encode local proximity information adaptively. The self-separation term is combined with GCN to learn cluster-friendly embeddings. A deep softmax auto-encoder is proposed to estimate the number of clusters.