TY - JOUR
T1 - Structural representation learning for user alignment across social networks
AU - Liu, Li
AU - Li, Xin
AU - Cheung, Kwok Wai
AU - Liao, Lejian
N1 - Funding Information:
The work is partially supported by the National Key R &D Program of China under Grant No.2017YFB0802305 and NSFC Grant 61772074 and 61806031, and in part by the Chongqing Research Program of Basic Research and Frontier Technology under Grants cstc2017jcyjAX0325, cstc2017jcy-jAX0406, and in part by the Science and Technology Research Program of Chongqing Municipal Education Commission under Grants KJQN201800638. This work was mostly done during Li Liu’s Ph.D. study at the Beijing Institute of Technology and his visit to Hong Kong Baptist University.
PY - 2020/9/1
Y1 - 2020/9/1
N2 - Aligning users across different social networks has become increasingly studied as an important task to social network analysis. In this paper, we propose a novel representation learning method that mainly exploits social structures for the network alignment. In particular, the proposed network embedding framework models the follower-ship and followee-ship of each user explicitly as input and output context vectors, while preserving the proximity of users with 'similar' followers and followees in the embedded space. We incorporate both known and predicted user anchors across the networks as constraints to facilitate the transfer of context information to achieve accurate user alignment. Both network embedding and user alignment are inferred under a unified optimization framework with negative sampling adopted to ensure scalability. Also, variants of the proposed framework, including the incorporation of higher-order structural features, are also explored for further boosting the alignment accuracy. Extensive experiments on large-scale social and academia network datasets demonstrate the efficacy of our proposed model compared with state-of-the-art methods.
AB - Aligning users across different social networks has become increasingly studied as an important task to social network analysis. In this paper, we propose a novel representation learning method that mainly exploits social structures for the network alignment. In particular, the proposed network embedding framework models the follower-ship and followee-ship of each user explicitly as input and output context vectors, while preserving the proximity of users with 'similar' followers and followees in the embedded space. We incorporate both known and predicted user anchors across the networks as constraints to facilitate the transfer of context information to achieve accurate user alignment. Both network embedding and user alignment are inferred under a unified optimization framework with negative sampling adopted to ensure scalability. Also, variants of the proposed framework, including the incorporation of higher-order structural features, are also explored for further boosting the alignment accuracy. Extensive experiments on large-scale social and academia network datasets demonstrate the efficacy of our proposed model compared with state-of-the-art methods.
KW - network embedding
KW - representation learning
KW - social networks
KW - User alignment
UR - http://www.scopus.com/inward/record.url?scp=85090324276&partnerID=8YFLogxK
U2 - 10.1109/TKDE.2019.2911516
DO - 10.1109/TKDE.2019.2911516
M3 - Journal article
AN - SCOPUS:85090324276
SN - 1041-4347
VL - 32
SP - 1824
EP - 1837
JO - IEEE Transactions on Knowledge and Data Engineering
JF - IEEE Transactions on Knowledge and Data Engineering
IS - 9
ER -