计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (3): 207-213.doi: 10.11896/jsjkx.250100093

• 数据库 & 大数据 & 数据科学 • 上一篇    下一篇

图正则化模糊自动编码器的重叠社区检测

邹晓阳, 鞠恒荣, 曹金鑫, 马星如, 黄嘉爽, 丁卫平   

  1. 南通大学人工智能与计算机学院 江苏 南通 226019
  • 收稿日期:2025-01-14 修回日期:2025-05-02 出版日期:2026-03-15 发布日期:2026-03-12
  • 通讯作者: 曹金鑫(alfred7c@ntu.edu.cn)
  • 作者简介:(13016989213@163.com)
  • 基金资助:
    国家自然科学基金(61976120,62006128,62102199,U2433216,62576178);江苏省自然科学基金(BK20231337);江苏省高等学校自然科学研究面上项目(24KJB520032)

Overlapping Community Detection with Graph Regularized Fuzzy Autoencoder

ZOU Xiaoyang, JU Hengrong, CAO Jinxin, MA Xingru, HUANG Jiashuang, DING Weiping   

  1. School of Artificial Intelligence and Computer Science, Nantong University, Nantong, Jiangsu 226019, China
  • Received:2025-01-14 Revised:2025-05-02 Published:2026-03-15 Online:2026-03-12
  • About author:ZOU Xiaoyang,born in 2001,postgra-duate.His main research interests include social network analysis and community detection.
    CAO Jinxin,born in 1987,Ph.D,lectu-rer,is a member of CCF(No.T2067M).His main research interests include data mining,machine learning,complex network analysis and community discovery.
  • Supported by:
    National Natural Science Foundation of China(61976120,62006128,62102199,U2433216,62576178),Natural Science Foundation of Jiangsu Province(BK20231337) and Natural Science Foundation of Jiangsu Higher Education Institutions of China(24KJB520032).

PDF (PC)

117

摘要： 在复杂网络分析中,挖掘社区结构是一个重要且具有挑战性的研究方向。现有的基于深度学习方法在图相关任务中取得了不错的效果,但鲜有处理社区检测任务,尤其是重叠社区检测,并且也未能充分挖掘和利用网络的拓扑结构信息。为此,提出了一种图正则化模糊自动编码器的重叠社区检测方法(Overlapping Community Detection with Graph Regularized Fuzzy AutoEncoder,FAE)。首先,运用自动编码器将网络拓扑编码为低维表示,进一步通过模糊C均值聚类形成模糊隶属度矩阵,随后解码模糊隶属度矩阵以重构网络拓扑。然后,将用于刻画网络中结构信息的图正则融入上述自动编码器。再者,融合后的自动编码器构成堆叠自动编码器,以获取深度模糊隶属度矩阵。最后,基于模糊集理论,使用深度模糊隶属度矩阵划分重叠社区。在3组人工网络和6个真实网络上的实验结果表明,该方法基于重叠标准互信息熵(ONMI)、杰卡德指数(Jaccard)、F1分数(F1-Score)的评估性能优于7种经典算法的大部分算法,展示了其在处理复杂网络重叠社区检测问题上的潜力。

关键词: 重叠社区发现, 堆叠自动编码器, 模糊C均值, 图正则, 深层模糊隶属度

Abstract: In complex network analysis,mining community structure is an important and challenging research topic.The existing deep learning-based methods have achieved good results in graph-related tasks,but they rarely deal with community detection tasks,especially overlapping community detection,and fail to fully mine and utilize network topology information.In response to these problems,this paper proposes an overlapping community detection with graph regularized fuzzy autoencode(FAE).Firstly,an autoencoder is employed to encode the network topology into a low-dimensional representation.This is followed by applying fuzzy C-means clustering to generate a fuzzy membership matrix,which is then decoded to reconstruct the network topology.Next,a graph regularization term－designed to characterize structural information within the network－is integrated into the aforementioned autoencoder framework.Subsequently,the autoencoder architecture with the graph regularization forms a stacked autoencoder to derive a deep fuzzy membership matrix.Finally,based on fuzzy set theory,the deep fuzzy membership matrix is utilized to partition overlapping communities.Experimental results on 3 groups of artificial networks and 6 real networks show that the performance of the proposed method evaluates by overlapping normalized mutual information(ONMI),Jaccard index(Jaccard) and F1-Score is superior to that of most of the 7 classical methods,demonstrating its potential in dealing with overlapping community detection problems.

Key words: Overlapping community discovery, Stacked autoencoder, Fuzzy C-means, Graph regularization, Deep fuzzy membership

中图分类号: 

  • TP391
[1]PENG Y,ZHAO Y,HU J.On the role of community structure in evolution of opinion formation:A new bounded confidence opinion dynamics[J].Information Sciences,2023,621:672-690.
[2]LIU Y,ZHU B,CHEN F,et al.Overlapping Network Community Detection Through Label Propagation Algorithm with K-Shell Aggregation[C]//2024 3rd International Conference on Computing,Communication,Perception and Quantum Technology(CCPQT).IEEE,2024:65-74.
[3]CHOUMANE A,AWADA A,HARKOUS A.Core expansion:a new community detection algorithm based on neighborhood overlap[J].Social Network Analysis and Mining,2020,10:1-11.
[4]ASMI K,LOTFI D,EL MARRAKI M.Overlapping community detection based on the union of all maximum spanning trees[J].Library Hi Tech,2020,38(2):276-292.
[5]HOLLOCOU A,BONALD T,LELARGE M.Multiple localcommunity detection[J].ACM SIGMETRICS Performance Evaluation Review,2018,45(3):76-83.
[6]NIU Y,KONG D,LIU L,et al.Overlapping community detection with adaptive density peaks clustering and iterative partition strategy[J].Expert Systems with Applications,2023,213:119213.
[7]SHAO M L,LIN Y J,PENG Q Y,et al.Learning graph deep autoencoder for anomaly detection in multi-attributed networks[J].Knowledge-Based Systems,2023,260:110084.
[8]QIN Y,JU W,WU H,et al.Learning graph ode for continuous-time sequential recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2024,36(7):3224-3236.
[9]LEE Y,PARK J H,OH S,et al.Derivation of prognostic contextual histopathological features from whole-slide images of tumours via graph deep learning[J].Nature Biomedical Engineering,2022,6(12):1452-1466.
[10]TANG W,TANG M,BAN M,et al.CSGVD:A deep learning approach combining sequence and graph embedding for source code vulnerability detection[J].Journal of Systems and Software,2023,199:111623.
[11]YANG L,CAO X C,HE D X,et al.Modularity based community detection with deep learning[C]//Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence.2016:2252-2258.
[12]HE C B,ZHENG Y L,CHENG J W,et al.Semi-supervised overlapping community detection in attributed graph with graph convolutional autoencoder[J].Information Sciences,2022,608:1464-1479.
[13]AL-AYYOUB M,AL-ANDOLI M,JARARWEH Y,et al.Improving fuzzy C-mean-based community detection in social networks using dynamic parallelism[J].Computers & Electrical Engineering,2019,74:533-546.
[14]DANESHFAR F,SOLEYMANBAIGI S,NAFISI A,et al.Elastic deep autoencoder for text embedding clustering by an improved graph regularization[J].Expert Systems with Applications,2024,238:121780.
[15]SETYAWAN R,ASRORI R B,SHIDIK G F,et al.Brain tumor identification using fcm threshold method and morphological area selection[C]//International Seminar on Application for Technology of Information and Communication.IEEE,2020:560-566.
[16]LEI Y,ZHOU Y,SHI J.Overlapping communities detection of social network based on hybrid C-means clustering algorithm[J].Sustainable Cities and Society,2019,47:101436.
[17]SHCHUR O,GÜNNEMANN S.Overlapping community detection with graph neural networks[J].arXiv:1909.12201,2019.
[18]YE F H,CHEN C,ZHENG Z B.Deep autoencoder-like nonnegative matrix factorization for community detection[C]//Procee-dings of the 27th ACM International Conference on Information and Knowledge Management.2018:1393-1402.
[19]WANG X,CUI P,WANG J,et al.Community preservingnetwork embedding[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2017:203-209.
[20]EPASTO A,LATTANZI S,PAES L R.Ego-splitting frame-work:From non-overlapping to overlapping clusters[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2017:145-154.
[21]ROZEMBERCZKI B,DAVIES R,SARKAR R,et al.Gemsec:Graph embedding with self clustering[C]//Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining.2019:65-72.
[22]LI P Z,HUANG L,WANG C D,et al.EdMot:An edge en-hancement approach for motif-aware community detection[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2019:479-487.
[23]FORTUNATO S.Benchmarks for testing community detection algorithms on directed and weighted graphs with overlapping communities[J].Physical Review E,2009,80(1):016118.
[24]MCAULEY J,LESKOVEC J.Discovering social circles in ego networks[J].Transactions on Knowledge Discovery from Data,2014,8(1):1-28.
[25]BERAHMAND K,MOHAMMADI M,SABERI-MOVAHEDF,et al.Graph regularized nonnegative matrix factorization for community detection in attributed networks[J].IEEE Transactions on Network Science and Engineering,2022,10(1):372-385.
[26]CHEN J Y,GONG Z G,MO J Q,et al.Self-training enhanced:Network embedding and overlapping community detection with adversarial learning[J].IEEE Transactions on Neural Networks and Learning Systems,2021,33(11):6737-6748.
[27]GIRVAN M,NEWMAN M E J.Community structure in social and biological networks[J].Proceedings of the National Academy of Sciences,2002,99(12):7821-7826.
[28]ZHU Q,LI H,HUANG J,et al.Hybrid functional brain network with first-order and second-order information for compu-ter-aided diagnosis of schizophrenia[J].Frontiers in Neuroscience,2019,13:603.
[29]YAZDANPARAST S,HAVENS T,JAMALABDOLLAHI M.Soft overlapping community detection in large-scale networks via fast fuzzy modularity maximization[J].IEEE Transactions on Fuzzy Systems,2020,29(6):1533-1543.
[30]LIU X,ZHANG M,LIU Y,et al.Semi-supervised community detection method based on generative adversarial networks[J].Journal of King Saud University-Computer and Information Sciences,2024,36(3):102008.
[31]ZHANG P.Evaluating accuracy of community detection usingthe relative normalized mutual information[J].Journal of Statistical Mechanics,2015,2015(11):P11006.
[32]MUKUNDA A,PIROUZ M.Influence-based community detection and ranking[C]//International Conference on Computational Science and Computational Intelligence.IEEE,2019:1341-1346.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发