Title | ||
---|---|---|
Adaptive Federated Dropout: Improving Communication Efficiency and Generalization for Federated Learning |
Abstract | ||
---|---|---|
To exploit the wealth of data generated and located at distributed entities such as mobile phones, a revolutionary decentralized machine learning setting, known as federated learning, enables multiple clients to collaboratively learn a machine learning model while keeping all their data on-device. However, the scale and decentralization of federated learning present new challenges. Communication b... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/INFOCOMWKSHPS51825.2021.9484526 | IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) |
Keywords | DocType | ISSN |
Training,Adaptation models,Computational modeling,Conferences,Distributed databases,Machine learning,Collaborative work | Conference | 2159-4228 |
ISBN | Citations | PageRank |
978-1-6654-0443-3 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nader Bouacida | 1 | 0 | 0.34 |
Jiahui Hou | 2 | 0 | 0.34 |
Hui Zang | 3 | 1052 | 77.25 |
Xin Liu | 4 | 3919 | 320.56 |