Deep Adaptive Graph Clustering via von Mises-Fisher Distributions

Author:

Wang Pengfei1ORCID,Wu Daqing2ORCID,Chen Chong3ORCID,Liu Kunpeng4ORCID,Fu Yanjie5ORCID,Huang Jianqiang3ORCID,Zhou Yuanchun1ORCID,Zhan Jianfeng6ORCID,Hua Xiansheng3ORCID

Affiliation:

1. Computer Network Information Center, Chinese Academy of Sciences, China

2. Peking University; DAMO Academy, Alibaba Group, China

3. DAMO Academy, Alibaba Group, China

4. Portland State University, USA

5. University of Central Florida, USA

6. Institute of Computing Technology, Chinese Academy of Sciences, China

Abstract

Graph clustering has been a hot research topic and is widely used in many fields, such as community detection in social networks. Lots of works combining auto-encoder and graph neural networks have been applied to clustering tasks by utilizing node attributes and graph structure. These works usually assumed the inherent parameters (i.e., size and variance) of different clusters in the latent embedding space are homogeneous, and hence the assigned probability is monotonous over the Euclidean distance between node embeddings and centroids. Unfortunately, this assumption usually does not hold since the size and concentration of different clusters can be quite different, which limits the clustering accuracy. In addition, the node embeddings in deep graph clustering methods are usually L2 normalized so that it lies on the surface of a unit hyper-sphere. To solve this problem, we proposed D eep A daptive G raph C lustering via von Mises-Fisher distributions, namely DAGC. DAGC assumes the node embeddings H can be drawn from a von Mises-Fisher distribution and each cluster k is associated with cluster inherent parameters ρ k which includes cluster center μ and cluster cohesion degree κ. Then we adopt an EM-like approach (i.e., 𝒫( H | ρ ) and 𝒫( ρ | H ), respectively) to learn the embedding and cluster inherent parameters alternately. Specifically, with the node embeddings, we proposed to update the cluster centers in an attraction-repulsion manner to make the cluster centers more separable. And given the cluster inherent parameters, a likelihood-based loss is proposed to make node embeddings more concentrated around cluster centers. Thus, DAGC can simultaneously improve the intra-cluster compactness and inter-cluster heterogeneity. Finally, extensive experiments conducted on four benchmark datasets have demonstrated that the proposed DAGC consistently outperforms the state-of-the-art methods, especially on imbalanced datasets.

Funder

Natural Science Foundation of China

Strategic Priority Research Program of CAS

Chinese Academy of Sciences Network Security and Informatization Special Application Demonstration

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications

Reference66 articles.

1. Clustering and Community Detection With Imbalanced Clusters

2. Jason Altschuler, Jonathan Niles-Weed, and Philippe Rigollet. 2017. Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS). 1961–1971.

3. Graph convolution for semi-supervised classification: Improved linear separability and out-of-distribution generalization;Baranwal Aseem;arXiv preprint arXiv:2102.06966,2021

4. Structural Deep Clustering Network

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3