Federated Learning (FL) allows machine learning algorithms to gain insights into a broad range of datasets located at different locations, enabling a privacy-preserving model development [1]. It was announced in 2016 by Google [2]. Clients contribute locally-trained models, the data never leaning their device!
In this simulation, we will be performing Federated Learning with a dataset of human activity with CNN.
First, upload the data in the folder data. Then you can run the notebook Federated Learning Simulation.ipynb
Ericka Bermudez for DBALab.
[1] Li, Qinbin, Zeyi Wen, Zhaomin Wu, Sixu Hu, Naibo Wang, Yuan Li, Xu Liu, and Bingsheng He. “A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection.” arXiv.org, 2019. https://arxiv.org/abs/1907.09693.
[2] Brendan, McMahan H, Eider Moore, Daniel Ramage, Seth Hampson, and Arcas, Blaise Agüera y. “Communication-Efficient Learning of Deep Networks from Decentralized Data.” arXiv.org, 2016. https://arxiv.org/abs/1602.05629.