基于模块度感知图自编码器的重叠社区发现模型  

Overlapping community detection model based on a modularity-aware graph autoencoder

作　　者：陈洁[1,2] 刘斌斌[1,2] 赵姝 张燕平[1,2] CHEN Jie;LIU Binbin;ZHAO Shu;ZHANG Yanping(School of Computer Science and Technology,Anhui University,Hefei 230601,China;Ministry of Education Key Laboratory of Computational Intelligence and Signal Processing,Anhui University,Hefei 230601,China)

机构地区：[1]安徽大学计算机科学与技术学院,合肥230601 [2]计算智能与信号处理教育部重点实验室(安徽大学),合肥230601

出　　处：《清华大学学报（自然科学版）》2024年第8期1319-1329,共11页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金项目(61876001);国家社会科学基金重大项目(18ZDA032)。

摘　　要：图自编码器模型作为网络表示学习的代表性方法,在链路预测和节点分类任务方面性能表现优异。然而,图自编码器模型在处理社区发现任务时通常只考虑局部节点连边的重建而忽略了社区全局结构的影响,尤其是在多个社区存在重叠节点的情况下,难以准确判断节点归属关系和社区分布。针对此问题,该文提出了一种面向重叠社区发现的无监督模块度感知图自编码器模型(modularity-aware graph autoencoder model for overlapping community detection,GAME),GAME采用一种高效的模块度损失函数,该函数在网络嵌入过程中保留社区关系的同时,能重构损失并更新编码器的参数,以提高模型针对重叠社区发现任务的性能,进而将GAME得到的社区隶属度矩阵以概率-节点形式进行社区分配。该文提出的GAME在10个公开数据集上进行实验验证,并与主流的基于表示学习的重叠社区发现模型进行对比。实验结果表明:在归一化互信息(normalized mutual information,NMI)评估指标下,GAME模型性能优于主流模型,证明该模型有效。[Objective]In the ever-expanding field of network science,the abstraction of complex entity relationships into network structures provides a foundation for understanding real-world interactions.The discovery of communities within these networks plays a pivotal role in identifying clusters of closely interconnected nodes.This process reveals latent patterns and functionalities inherent in the intricate fabric of reality,proving invaluable for tracking dynamic network behaviors and assessing community influences.These influences span a range of phenomena,from rumor propagation to virus outbreaks and tumor evolution.A notable characteristic of these communities is their overlapping nature,with participants often straddling multiple community boundaries.This characteristic adds an additional layer of complexity to the exploration of network structures,making the discovery of overlapping communities imperative for a comprehensive understanding of network structures and functional dynamics.[Methods]Within the realm of network science,network representation learning algorithms have significantly enriched the pursuit of community discovery.These algorithms adeptly transform complex network information into lower-dimensional vectors,effectively maintaining the underlying network structure and attribute information.Such representations prove invaluable for subsequent graph processing tasks,including but not limited to link prediction,node classification,and community discovery.Among these algorithms,the graph autoencoder model is a prominent representative,demonstrating efficiency in learning network embeddings and finding applications in diverse community discovery tasks.However,a limitation inherent in traditional graph autoencoder models is their predominant focus on local node-edge reconstruction.This focus often overlooks the crucial influence of community structure,particularly in scenarios featuring overlapping nodes across multiple communities.This inherent challenge makes it difficult to precisely determine node a

关 键 词：社区发现 重叠社区 图自编码器 模块度最大化 社区隶属度矩阵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]