作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2021, Vol. 47 ›› Issue (10): 52-60. doi: 10.19678/j.issn.1000-3428.0059629

• 人工智能与模式识别 • 上一篇    下一篇

基于稀疏子空间聚类的多层网络社团检测

孙登第1, 凌媛1, 丁转莲2, 罗斌1   

  1. 1. 安徽大学 计算机科学与技术学院, 合肥 230601;
    2. 安徽大学 互联网学院, 合肥 230039
  • 收稿日期:2020-10-01 修回日期:2020-11-05 发布日期:2020-11-18
  • 作者简介:孙登第(1983-),男,副教授、博士,主研方向为机器学习、计算机视觉、网络数据挖掘;凌媛,硕士研究生;丁转莲,讲师、博士;罗斌,教授、博士。
  • 基金资助:
    国家自然科学基金青年科学基金“基于子空间学习的多层网络社团协同检测研究”(61906002);国家自然科学基金重点国际合作项目“遥感影像地面区域变化的结构化建模与检测方法研究”(61860206004)。

Multi-Layer Network Community Detection Based on Sparse Subspace Clustering

SUN Dengdi1, LING Yuan1, DING Zhuanlian2, LUO Bin1   

  1. 1. School of Computer Science and Technology, Anhui University, Hefei 230601, China;
    2. School of Internet, Anhui University, Hefei 230039, China
  • Received:2020-10-01 Revised:2020-11-05 Published:2020-11-18

摘要: 现有的子空间聚类方法大多只适用于单层网络,或者仅对多层网络中每层的聚类结果简单地进行平均,未考虑每层网络中包含信息量不同的特点,致使聚类性能受限。针对该问题,提出一种面向多层网络的稀疏子空间聚类方法。将距离正则项和非负约束条件集成到稀疏子空间聚类框架中,从而在聚类时能够同时利用数据的全局信息和局部信息进行图学习。此外,通过引入稀疏约束使学习到的图具有更清晰的聚类结构,并设计迭代算法进行优化求解。在多个真实数据集上的实验结果表明,该方法能够挖掘网络不同层的互补信息,得到准确的一致性联合稀疏表示,有效提高社团聚类性能。

关键词: 高维数据, 子空间聚类, 稀疏表示, 社团检测, 复杂网络

Abstract: The existing subspace clustering methods are only applicable to single-layer networks, or just average the clustering results of each layer in the multi-layer network.They fail to consider the different amounts of information contained in each layer, which causes a reduction in the subspace clustering performance.To address the problem, a sparse subspace clustering method for multi-layer networks is proposed.Firstly, a distance regularization term and a non-negative constraint are jointly integrated into the framework of sparse subspace clustering, which enables the method to simultaneously exploit the global and local information of data for graph learning during clustering.In addition, the sparse constraint is introduced to provide the learned graph with a clear clustering structure, and an iterative algorithm is designed to optimize the solution.Experimental results on multiple real datasets show that the proposed method can mine the complementary information of different layers of the network, obtain an accurate consistent joint sparse representation, and effectively improve the community clustering performance of multi-layer networks.

Key words: high-dimensional data, subspace clustering, sparse representation, community detection, complex network

中图分类号: