University of Oulu

Z. Ren, M. Mukherjee, M. Bennis and J. Lloret, "Multikernel Clustering via Non-Negative Matrix Factorization Tailored Graph Tensor Over Distributed Networks," in IEEE Journal on Selected Areas in Communications, vol. 39, no. 7, pp. 1946-1956, July 2021, doi: 10.1109/JSAC.2020.3041396

Multikernel clustering via non-negative matrix factorization tailored graph tensor over distributed networks

Saved in:
Author: Ren, Zhenwen1,2; Mukherjee, Mithun3; Bennis, Mehdi4;
Organizations: 1Department of National Defence Science and Technology, Southwest University of Science and Technology, Mianyang, China, 621010
2Department of Computer Science, Nanjing University of Science and Technology, Nanjing, China, 210094
3Department of Electronic and Computer Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China
4Centre of Wireless Communication, University of Oulu, Finland
5Instituto de Investigación para la Gestión Integrada de Zonas Costeras (IGIC), Universitat Politecnica de Valencia, 46022 Valencia, Spain
6School of Computing and Digital Technologies, Staffordshire University, Stoke, UK
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 4.6 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2021-10-12


Next-generation wireless networks are witnessing an increasing number of clustering applications, and produce a large amount of non-linear and unlabeled data. In some degree, single kernel methods face the challenging problem of kernel choice. To overcome this problem for non-linear data clustering, multiple kernel graph-based clustering (MKGC) has attracted intense attention in recent years. However, existing MKGC methods suffer from two common problems: (1) they mainly aim to learn a consensus kernel from multiple candidate kernels, slight affinity graph learning, such that cannot fully exploit the underlying graph structure of non-linear data; (2) they disregard the high-order correlations between all base kernels, which cannot fully capture the consistent and complementary information of all kernels. In this paper, we propose a novel non-negative matrix factorization (NMF) tailored graph tensor MKGC method for non-linear data clustering, namely TMKGC. Specifically, TMKGC integrates NMF and graph learning together in kernel space so as to learn multiple candidate affinity graphs. Afterwards, the high-order structure information of all candidate graphs is captured in a 3-order tensor kernel space by introducing tensor singular value decomposition based tensor nuclear norm, such that an optimal affinity graph can be obtained subsequently. Based on the alternating direction method of multipliers, the effective local and distributed solvers are elaborated to solve the proposed objective function. Extensive experiments have demonstrated the superiority of TMKGC compared to the state-of-the-art MKGC methods.

see all

Series: IEEE journal on selected areas in communications
ISSN: 0733-8716
ISSN-E: 1558-0008
ISSN-L: 0733-8716
Volume: 39
Issue: 7
Pages: 1946 - 1956
DOI: 10.1109/JSAC.2020.3041396
Type of Publication: A1 Journal article – refereed
Field of Science: 213 Electronic, automation and communications engineering, electronics
Funding: This research was supported by the Sichuan Science and Technology Program (Grant nos. 2019ZDZX0043 and 2020ZDZX0014), the Key Lab of Film and TV Media Technology of Zhejiang Province (Grant no. 2020E10015), the Natural Science Foundation of Chongqing (Grant no. cstc2020jcyj-msxmX0473), the Scientific Research Fund of Sichuan Provincial Education Department (Grant no. 17ZB0441), and the Scientific Research Fund of Southwest University of Science and Technology (Grant no. 17zx7137).
Copyright information: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.