Zobrazeno 1 - 10
of 79
pro vyhledávání: '"Yingxia Shao"'
Publikováno v:
Data Science and Engineering, Vol 4, Iss 1, Pp 76-92 (2019)
Abstract Ever since the social networks became the focus of a great number of researches, the privacy risks of published network data have also raised considerable concerns. To evaluate users’ privacy risks, researchers have developed methods to de
Externí odkaz:
https://doaj.org/article/3958ccc04e7b43bbbea642755022a0bc
Publikováno v:
IEEE Access, Vol 7, Pp 105470-105478 (2019)
Low-rank decomposition is an effective way to decrease the model size of convolutional neural networks (CNNs). Nevertheless, selecting the layer-specific rank is a difficult task, because the layers are not equally redundant. The previous methods are
Externí odkaz:
https://doaj.org/article/f5e85b049959423abb77faae6629d8c4
Publikováno v:
Data Science and Engineering, Vol 5, Iss 4, Pp 331-332 (2020)
Externí odkaz:
https://doaj.org/article/33e8ed2283ec4b07a33afb01683c1ed7
Autor:
Yingxia SHAO, Shicong FENG
Publikováno v:
大数据, Vol 3, p 2017018 (2017)
Social network analysis (SNA) is a general and effective approach of studying the complex relationship patterns among social members.Public security field was focused.Firstly,the theory of SNA was introduced,and then three applications of applyin
Externí odkaz:
https://doaj.org/article/e3f9d947d38244329c0ddf8352fb187a
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering. :1-14
Autor:
Xupeng Miao, Wentao Zhang, Yuezihan Jiang, Fangcheng Fu, Yingxia Shao, Lei Chen, Yangyu Tao, Gang Cao, Bin Cui
Publikováno v:
The VLDB Journal. 32:717-736
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering. 34:4119-4132
Wide models such as generalized linear models and factorization-based models have been extensively used in various predictive applications, e.g., recommendation systems. Due to the memory bounded property of the models, the performance improvement on
Publikováno v:
Proceedings of the VLDB Endowment. 15:1937-1950
Graph neural networks (GNNs) have emerged due to their success at modeling graph data. Yet, it is challenging for GNNs to efficiently scale to large graphs. Thus, distributed GNNs come into play. To avoid communication caused by expensive data moveme
Publikováno v:
Proceedings of the 31st ACM International Conference on Information & Knowledge Management.
Publikováno v:
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.