https://github.com/shaoxiongji/fed-att
Attentive Federated Learning for Private NLM
https://github.com/shaoxiongji/fed-att
attention-mechanism deep-learning federated-learning language-modeling pytorch
Last synced: about 1 year ago
JSON representation
Attentive Federated Learning for Private NLM
- Host: GitHub
- URL: https://github.com/shaoxiongji/fed-att
- Owner: shaoxiongji
- License: mit
- Created: 2018-12-17T11:45:55.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2024-07-25T10:13:51.000Z (almost 2 years ago)
- Last Synced: 2025-03-29T16:23:10.720Z (about 1 year ago)
- Topics: attention-mechanism, deep-learning, federated-learning, language-modeling, pytorch
- Language: Python
- Homepage: https://arxiv.org/abs/1812.07108
- Size: 10.7 KB
- Stars: 61
- Watchers: 4
- Forks: 17
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Attentive Federated Learning
This repository contains the code for the paper [Learning Private Neural Language Modeling with Attentive Aggregation](https://arxiv.org/abs/1812.07108), which is an attentive extention of federated aggregation. A brief introductionary blog is avaiable [here](https://shaoxiongji.github.io/2019/07/11/attentive-federated-learning.html).
Further reference: a universal federated learning repository implemented by PyTorch - [Federated Learning - PyTorch](https://github.com/shaoxiongji/federated-learning).
## Run
Refer to the ```README.md``` under the data folder and download the datasets into their corresponding folders. Enter the source code folder to run the scripts with arguments assigned using ```argparse``` package.
```
cd src
python run.py
```
See configs in ```src/utils/options.py```
## Requirements
Python 3.6
PyTorch 0.4.1
## Cite
```
@inproceedings{ji2019learning,
title={Learning Private Neural Language Modeling with Attentive Aggregation},
author={Ji, Shaoxiong and Pan, Shirui and Long, Guodong and Li, Xue and Jiang, Jing and Huang, Zi},
booktitle={International Joint Conference on Neural Networks (IJCNN)},
year={2019}
}
```