Zobrazeno 1 - 10
of 307
pro vyhledávání: '"Wang Shaofan"'
Graph Neural Networks (GNNs) have excelled in handling graph-structured data, attracting significant research interest. However, two primary challenges have emerged: interference between topology and attributes distorting node representations, and th
Externí odkaz:
http://arxiv.org/abs/2411.11284
Publikováno v:
IEEE Access, Vol 9, Pp 12750-12761 (2021)
The traditional financial models used in bond default mainly focus on the analysis and prediction of bonds issued by listed companies, and they lack early warning abilities for a large number of bonds of nonlisted companies. At the same time, there i
Externí odkaz:
https://doaj.org/article/19687b497439441785e01f1e626c4c23
Publikováno v:
AUTEX Research Journal, Vol 21, Iss 3, Pp 341-351 (2020)
Fiber injection molding is an innovative approach for the manufacturing of nonwoven preforms but products currently lack a homogeneous fiber distribution. Based on a mold-integrated monitoring system, the uniformity of the manufactured preforms will
Externí odkaz:
https://doaj.org/article/f75bc627dca4432e9ffd3acca4d4c8c9
Autor:
Wang, Jinlu, Guo, Jipeng, Sun, Yanfeng, Gao, Junbin, Wang, Shaofan, Yang, Yachao, Yin, Baocai
Graph neural networks (GNNs) demonstrate a robust capability for representation learning on graphs with complex structures, showcasing superior performance in various applications. The majority of existing GNNs employ a graph convolution operation by
Externí odkaz:
http://arxiv.org/abs/2401.15584
Publikováno v:
IAENG International Journal of Applied Mathematics. Nov2024, Vol. 54 Issue 11, p2459-2469. 11p.
Publikováno v:
In Applied Catalysis O: Open December 2024 197
Publikováno v:
In Children and Youth Services Review November 2024 166
Publikováno v:
In Expert Systems With Applications 1 March 2025 262
Domain adaptation aims to leverage information from the source domain to improve the classification performance in the target domain. It mainly utilizes two schemes: sample reweighting and feature matching. While the first scheme allocates different
Externí odkaz:
http://arxiv.org/abs/2109.02990
Autor:
Peng, Jingxuan, Wei, Zhonghua, Wang, Shaofan, Chen, Yanyan, Li, Yongxing, Wang, Zijia, Taku, Fujiyama
Publikováno v:
In Transportation Research Part C June 2024 163