https://github.com/ari-dasci/s-tutorialfl
DaSCI Tutorial on Federated Learning is part of our goal for knowledge transfer to society
https://github.com/ari-dasci/s-tutorialfl
tutorial-code tutorial-exercises
Last synced: 19 days ago
JSON representation
DaSCI Tutorial on Federated Learning is part of our goal for knowledge transfer to society
- Host: GitHub
- URL: https://github.com/ari-dasci/s-tutorialfl
- Owner: ari-dasci
- Created: 2023-03-09T18:01:40.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-09-06T10:19:39.000Z (almost 3 years ago)
- Last Synced: 2025-02-27T17:13:51.277Z (over 1 year ago)
- Topics: tutorial-code, tutorial-exercises
- Language: Jupyter Notebook
- Homepage: https://dasci.es/knowledge-transfer/software/
- Size: 1.64 MB
- Stars: 4
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
This repository contains the python notebooks of the tutorial on Federated Learning (FL). It includes examples of how to solve problems either at Horizontal (HFL) or Vertical (VFL) Federated Learning scenarios, using [TensorFlow Federated (TFF)](https://github.com/tensorflow/federated), [Flower](https://github.com/adap/flower) and [FATE](https://github.com/FederatedAI/FATE) frameworks.
It is divided into different notebooks:
* Comparative study of whether to consider the usage of FL (TFF)
* Use case 1. Image classification using deep learning in HFL (TFF, Flower and FATE)
* Use case 2. Sentiment analysis using deep learning in HFL (TFF and Flower)
* Use case 3. Decision trees in VFL (FATE)
* Use case 4. Introducing differential privacy (TFF)
* Use case 5. Clustering with k-means in HFL (TFF)
* Use case 6. Clustering with k-means in VFL (FATE)