TY - JOUR
T1 - Deep Attributed Network Embedding by Preserving Structure and Attribute Information
AU - Hong, Richang
AU - He, Yuan
AU - Wu, Le
AU - Ge, Yong
AU - Wu, Xindong
N1 - Funding Information:
Manuscript received July 8, 2018; revised November 5, 2018; accepted January 18, 2019. Date of publication March 1, 2019; date of current version February 17, 2021. This work was supported in part by the National Key Research and Development Program of China under Grant 2017YFB1002203, in part by the National Natural Science Foundation of China under Grant 61602147, Grant 61602234, Grant 61572032, and Grant 61722204, in part by the Anhui Provincial Natural Science Foundation under Grant 1708085QF155, and in part by the Fundamental Research Funds for the Central Universities under Grant JZ2018HGTB0230. This paper was recommended by Associate Editor E. Chen. (Corresponding author: Le Wu.) R. Hong, Y. He, and L. Wu are with the School of Computer and Information, Hefei University of Technology, Hefei 230009, China (e-mail: [email protected]; [email protected]; [email protected]).
Publisher Copyright:
© 2013 IEEE.
PY - 2021/3
Y1 - 2021/3
N2 - Network embedding aims to learn distributed vector representations of nodes in a network. The problem of network embedding is fundamentally important. It plays crucial roles in many applications, such as node classification, link prediction, and so on. As the real-world networks are often sparse with few observed links, many recent works have utilized the local and global network structure proximity with shallow models for better network embedding. In reality, each node is usually associated with rich attributes. Some attributed network embedding models leveraged the node attributes in these shallow network embedding models to alleviate the data sparsity issue. Nevertheless, the underlying structure of the network is complex. What is more, the connection between the network structure and node attributes is also hidden. Thus, these previous shallow models fail to capture the nonlinear deep information embedded in the attributed network, resulting in the suboptimal embedding results. In this paper, we propose a deep attributed network embedding framework to capture the complex structure and attribute information. Specifically, we first adopt a personalized random walk-based model to capture the interaction between network structure and node attributes from various degrees of proximity. After that, we construct an enhanced matrix representation of the attributed network by summarizing the various degrees of proximity. Then, we design a deep neural network to exploit the nonlinear complex information in the enhanced matrix for network embedding. Thus, the proposed framework could capture the complex attributed network structure by preserving both the various degrees of network structure and node attributes in a unified framework. Finally, empirical experiments show the effectiveness of our proposed framework on a variety of network embedding-based tasks.
AB - Network embedding aims to learn distributed vector representations of nodes in a network. The problem of network embedding is fundamentally important. It plays crucial roles in many applications, such as node classification, link prediction, and so on. As the real-world networks are often sparse with few observed links, many recent works have utilized the local and global network structure proximity with shallow models for better network embedding. In reality, each node is usually associated with rich attributes. Some attributed network embedding models leveraged the node attributes in these shallow network embedding models to alleviate the data sparsity issue. Nevertheless, the underlying structure of the network is complex. What is more, the connection between the network structure and node attributes is also hidden. Thus, these previous shallow models fail to capture the nonlinear deep information embedded in the attributed network, resulting in the suboptimal embedding results. In this paper, we propose a deep attributed network embedding framework to capture the complex structure and attribute information. Specifically, we first adopt a personalized random walk-based model to capture the interaction between network structure and node attributes from various degrees of proximity. After that, we construct an enhanced matrix representation of the attributed network by summarizing the various degrees of proximity. Then, we design a deep neural network to exploit the nonlinear complex information in the enhanced matrix for network embedding. Thus, the proposed framework could capture the complex attributed network structure by preserving both the various degrees of network structure and node attributes in a unified framework. Finally, empirical experiments show the effectiveness of our proposed framework on a variety of network embedding-based tasks.
KW - Attribute proximity
KW - attributed network embedding
KW - high-order proximity
UR - http://www.scopus.com/inward/record.url?scp=85101084946&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85101084946&partnerID=8YFLogxK
U2 - 10.1109/TSMC.2019.2897152
DO - 10.1109/TSMC.2019.2897152
M3 - Article
AN - SCOPUS:85101084946
SN - 2168-2216
VL - 51
SP - 1434
EP - 1445
JO - IEEE Transactions on Systems, Man, and Cybernetics: Systems
JF - IEEE Transactions on Systems, Man, and Cybernetics: Systems
IS - 3
M1 - 8654725
ER -