Abstract | ||
---|---|---|
The current standalone deep learning framework tends to result in overfitting and low utility. This problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to aggregate local model updates. Server-based solutions are prone to the problem of a sin... |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/TPDS.2020.2996273 | IEEE Transactions on Parallel and Distributed Systems |
Keywords | DocType | Volume |
Machine learning,Biological system modeling,Data models,Collaboration,Servers,Privacy,Computational modeling | Journal | 31 |
Issue | ISSN | Citations |
11 | 1045-9219 | 13 |
PageRank | References | Authors |
0.54 | 0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lingjuan Lyu | 1 | 13 | 0.54 |
Jiangshan Yu | 2 | 86 | 11.35 |
Karthik Nandakumar | 3 | 1878 | 79.89 |
Yitong Li | 4 | 20 | 4.39 |
Xingjun Ma | 5 | 126 | 14.19 |
Jiong Jin | 6 | 511 | 46.66 |
Han Yu | 7 | 639 | 48.71 |
Kee Siong Ng | 8 | 13 | 1.22 |