https://github.com/shaoxiongji/federated-learning

A PyTorch Implementation of Federated Learning http://doi.org/10.5281/zenodo.4321561
https://github.com/shaoxiongji/federated-learning

deep-learning federated-learning pytorch

Last synced: 1 day ago
JSON representation

A PyTorch Implementation of Federated Learning http://doi.org/10.5281/zenodo.4321561

• Host: GitHub
• URL: https://github.com/shaoxiongji/federated-learning
• Owner: shaoxiongji
• License: mit
• Created: 2018-03-30T10:44:46.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2024-07-25T10:13:30.000Z (4 months ago)
• Last Synced: 2024-08-03T16:09:34.465Z (3 months ago)
• Topics: deep-learning, federated-learning, pytorch
• Language: Python
• Homepage: http://doi.org/10.5281/zenodo.4321561
• Size: 30.3 KB
• Stars: 1,222
• Watchers: 14
• Forks: 354
• Open Issues: 16
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-federated-computing - PyTorch Federated Learning - Github

README

        
# Federated Learning [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4321561.svg)](https://doi.org/10.5281/zenodo.4321561)

This is partly the reproduction of the paper of [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://arxiv.org/abs/1602.05629)   

Only experiments on MNIST and CIFAR10 (both IID and non-IID) is produced by far.

Note: The scripts will be slow without the implementation of parallel computing. 

## Requirements

python>=3.6  

pytorch>=0.4

## Run

The MLP and CNN models are produced by:

> python [main_nn.py](main_nn.py)

Federated learning with MLP and CNN is produced by:

> python [main_fed.py](main_fed.py)

See the arguments in [options.py](utils/options.py). 

For example:

> python main_fed.py --dataset mnist --iid --num_channels 1 --model cnn --epochs 50 --gpu 0  

`--all_clients` for averaging over all client models

NB: for CIFAR-10, `num_channels` must be 3.

## Results

### MNIST

Results are shown in Table 1 and Table 2, with the parameters C=0.1, B=10, E=5.

Table 1. results of 10 epochs training with the learning rate of 0.01

| Model     | Acc. of IID | Acc. of Non-IID|

| -----     | -----       | ----           |

| FedAVG-MLP|  94.57%     | 70.44%         |

| FedAVG-CNN|  96.59%     | 77.72%         |

Table 2. results of 50 epochs training with the learning rate of 0.01

| Model     | Acc. of IID | Acc. of Non-IID|

| -----     | -----       | ----           |

| FedAVG-MLP| 97.21%      | 93.03%         |

| FedAVG-CNN| 98.60%      | 93.81%         |

## Ackonwledgements

Acknowledgements give to [youkaichao](https://github.com/youkaichao).

## References

McMahan, Brendan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Artificial Intelligence and Statistics (AISTATS), 2017.

## Cite As

Shaoxiong Ji. (2018, March 30). A PyTorch Implementation of Federated Learning. Zenodo. http://doi.org/10.5281/zenodo.4321561