@article{82403180759e4ede8fca813adbaa8347,
title = "Inductive Representation Learning via CNN for Partially-Unseen Attributed Networks",
abstract = "Network embedding aims to map a complex network into a low-dimensional vector space while maximally preserving the properties of the original network. An attributed network is a typical real-world network that models the relationships and attributes of real-world entities. Its analysis is of great significance in many applications. However, most such networks are incomplete with partially-known attributes, links and labels. Traditional network embedding methods are designed for a complete network and cannot be applied to a network with incomplete information. Thus, this work proposes an inductive embedding model to learn the robust representations for a partially-unseen attributed network. It is designed based on a multi-core convolutional neural network and a semi-supervised learning mechanism, which can preserve the properties of such a network and generate the effective representations for unseen nodes in a model training process. We evaluate its performance on the task of inductive node classification and community detection via three real-world attributed networks. Experimental results show that it significantly outperforms the state-of-the-art. ",
keywords = "Attributed network, convolutional neural network, deep learning, inductive learning, network embedding",
author = "Zhongying Zhao and Hui Zhou and Liang Qi and Liang Chang and Zhou, {Meng Chu}",
note = "Funding Information: Manuscript received July 7, 2020; revised December 2, 2020; accepted December 30, 2020. Date of publication January 5, 2021; date of current version March 17, 2021. This research was supported by the National Natural Science Foundation of China under Grants 62072288, 61702306, 61303167, 71772107, 61433012, U1711263, U1811264, the Taishan Scholar Program of Shandong Province (Grant No. ts20190936), the Natural Science Foundation of Shandong Province (Grant No. ZR2018BF013), the National Key R&D Plan (Grant No. 2018YFC0831002), the Innovative Research Foundation of Qingdao (Grant No. 18-2-2-41-jch), the Key Project of Industrial Transformation and Upgrading in China (No. TC170A5SW), the SDUST Research Found for Innovative Team (Grant No. 2015TDJH102), Open Project of Guangxi Key Laboratory of Trusted Software (Grant No. KX201535), Open Project from the CAS Key Lab of Network Data Science and Technology (Grant No. CASNDST202007), Open Project Foundation of Intelligent Information Processing Key Laboratory of Shanxi Province (Grant No. CICIP2020001) and in part by the Ministry of Science and Higher Education of the Russian Federation as part of World-class Research Center program: Advanced Digital Technologies under Contract No. 075-15-2020-903. Recommended for acceptance by Dr.MyT.Thai. (Corresponding author: MengChu Zhou.) Zhongying Zhao, Hui Zhou, and Liang Qi are with the School of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, Shandong, China (e-mail: zzysuin@163.com; zhouhui1026@foxmail.com; qiliangsdkd@163.com). Publisher Copyright: {\textcopyright} 2013 IEEE.",
year = "2021",
month = jan,
day = "1",
doi = "10.1109/TNSE.2020.3048902",
language = "English (US)",
volume = "8",
pages = "695--706",
journal = "IEEE Transactions on Network Science and Engineering",
issn = "2327-4697",
publisher = "IEEE Computer Society",
number = "1",
}