TY - JOUR
T1 - Hybrid Embedding via Cross-layer Random Walks on Multiplex Networks
AU - Shi, Benyun
AU - Zhong, Jianan
AU - Qiu, Hongjun
AU - Bao, Qing
AU - Liu, Kai
AU - Liu, Jiming
N1 - Funding Information:
Manuscript received November 16, 2019; revised August 26, 2020; accepted April 13, 2021. Date of publication April 19, 2021; date of current version July 7, 2021. The authors would like to acknowledge the funding support from the Hong Kong Research Grants Council under Grants RGC/ HKBU12201619 RGC/HKBU12201318, and RGC/HKBU12202220, in part by the National Natural Science Foundation of China under Grant 61806061, and in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LQ19F030011 for the research work being presented in this article. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Recommended for acceptance by Dr. My T. Thai. (Corresponding authors: Benyun Shi and Jiming Liu.) Benyun Shi is with the School of Computer Science and Technology, Nanjing Tech University, Nanjing 211800, China (e-mail: benyunshi@ outlook.com).
Publisher Copyright:
© 2013 IEEE.
PY - 2021/4
Y1 - 2021/4
N2 - Node embedding aims to encode network nodes as a set of low-dimensional vectors while preserving certain structural properties of the network. In recent years, extensive studies have been conducted to preserve network communities, i.e., structural proximity of network nodes. However, few of them have focused on preserving the structural equivalence of network nodes, which describes the similarity of structural roles between network nodes. In this paper, we focus on a hybrid network embedding problem of how to flexibly and simultaneously preserve both structural proximity and equivalence. Here, we introduce the concept of graphlet degree vector (GDV) to describe structure roles of network nodes, and further measure structural equivalence based on their similarity. Specifically, we capture both structural proximity and equivalence by building a multiplex network, where both unsupervised and semi-supervised cross-layer random walk (CL-Walk) methods are implemented. By carrying out experiments on both synthetic and real-world datasets, we evaluate the performance of the proposed CL-Walk methods for the tasks of node clustering, node classification, and label prediction. The experimental results indicate that the CL-Walk method outperforms several state-of-the-art methods when both structural proximity and structural equivalence are relevant to specific network analytic task.
AB - Node embedding aims to encode network nodes as a set of low-dimensional vectors while preserving certain structural properties of the network. In recent years, extensive studies have been conducted to preserve network communities, i.e., structural proximity of network nodes. However, few of them have focused on preserving the structural equivalence of network nodes, which describes the similarity of structural roles between network nodes. In this paper, we focus on a hybrid network embedding problem of how to flexibly and simultaneously preserve both structural proximity and equivalence. Here, we introduce the concept of graphlet degree vector (GDV) to describe structure roles of network nodes, and further measure structural equivalence based on their similarity. Specifically, we capture both structural proximity and equivalence by building a multiplex network, where both unsupervised and semi-supervised cross-layer random walk (CL-Walk) methods are implemented. By carrying out experiments on both synthetic and real-world datasets, we evaluate the performance of the proposed CL-Walk methods for the tasks of node clustering, node classification, and label prediction. The experimental results indicate that the CL-Walk method outperforms several state-of-the-art methods when both structural proximity and structural equivalence are relevant to specific network analytic task.
KW - Network embedding
KW - Structural proximity
KW - Structural equivalence
KW - Multiplex networks
KW - Graphlet degree vector
KW - CCross-layer random walks
UR - http://www.scopus.com/inward/record.url?scp=85104613788&partnerID=8YFLogxK
U2 - 10.1109/TNSE.2021.3073956
DO - 10.1109/TNSE.2021.3073956
M3 - Journal article
AN - SCOPUS:85104613788
SN - 2327-4697
VL - 8
SP - 1815
EP - 1827
JO - IEEE Transactions on Network Science and Engineering
JF - IEEE Transactions on Network Science and Engineering
IS - 2
ER -