Gengrun WANG

Dr. Gengrun WANG


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 April 2023 in Electronics
Verified
Journal Article
Open access
PDF file
TLTianliang Lei
Tianliang Lei
LJLixin Ji
Lixin Ji
GWGengrun WANG
Gengrun WANG
SLShu-Xin Liu
Shu-Xin Liu
LWLan Wu
Lan Wu
FPFei Pan
Fei Pan
Cross-social network user identification refers to finding users with the same identity in multiple social networks, which is widely used in the cross-network recommendation, link prediction, personality recommendation, and data mining. At present, the traditional method is to obtain network structure information from neighboring nodes through graph convolution, and embed social networks into the low-dimensional vector space. However, as the network depth increases, the effect of the model will decrease. Therefore, in order to better obtain the network embedding representation, a Transformer-based user alignment model (TUAM) across social networks is proposed. This model converts the node information and network structure information from the graph data form into sequence data through a specific encoding method. Then, it inputs the data to the proposed model to learn the low-dimensional vector representation of the user. Finally, it maps the two social networks to the same feature space for alignment. Experiments on real datasets show that compared with GAT, TUAM improved ACC@10 indicators by 11.61% and 16.53% on Facebook–Twitter and Weibo–Douban datasets, respectively. This illustrates that the proposed model has a better performance compared to other user alignment models.

10 June 2014 in IEEJ Transactions on Electrical and Electronic Engineering
Verified
Journal Article
Closed access
PDF file
GWGengrun WANG
Gengrun WANG
DGDaoxing Guo
Daoxing Guo
ALAijun Liu
Aijun Liu
BZBangning Zhang
Bangning Zhang

1 January 2026 in IET Communications
Verified
Journal Article
Open access
PDF file
GWGengrun WANG
Gengrun WANG
KWKai Wang
Kai Wang
WYWei You
Wei You
SLShuo Liu
Shuo Liu
User identity linkage is the core task of cross‐network user behaviour analysis. Conventional methods build user matching links by utilising explicit auxiliary information such as user registration metadata. In this paper, we propose a spatiotemporal trajectory attention (STTAT) model for user identity linkage based on user check‐in records in cyberspace. STTAT exploits the powerful feature extraction ability of graph attention to capture fine‐grained similarities between trajectory segments and matches segments belonging to the identical user via latent characteristics, including dwell point distribution and sequential mobility patterns. Experimental results show STTAT achieves an ACC@1 of 88% and a weighted‐ F 1 of 0.859 on Geolife, and an ACC@1 of 62% and a weighted‐ F 1 of 0.623 on Gowalla. Comprehensive comparisons verify that STTAT outperforms existing models with consistent gains in both accuracy and recall.

12 February 2015 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
GWGengrun WANG
Gengrun WANG
BZBangning Zhang
Bangning Zhang
KPKegang Pan
Kegang Pan
ALAijun Liu
Aijun Liu
DGDaoxing Guo
Daoxing Guo
Channels of mobile satellite communications are affected by multipath fading and shadowing attenuation. At the same time, diversity gains are believed to improve the transmission reliability in fading channels. Considering that the traditional Space-Time Coding (STC) is not suitable for the cooperative mobile satellite communication, in this paper, a new cooperative mobile satellite communication system is proposed based on the Dynamic Space-Time Coding (D-STC). The transmitting energy of the proposed scheme is saved by avoiding forwarding erroneous signals in cooperative users. Meanwhile, this system benefits from diversity gains and the transmission is robust. Additionally, a closed-form expression of the outage probability for the proposed scheme is derived, and then it is demonstrated that this scheme is much better than the existing noncooperative scheme and schemes with traditional STCs in the outage performance. Finally, the analytical result is supported and validated by numerical simulations.