Quantum Federated Learning with PennyLane and Flower

This tutorial demonstrates how to implement Quantum Federated Learning using PennyLane for a hybrid quantum-classical neural network and Flower for federated learning. This example uses Flower Datasets to download, partition and preprocess the CIFAR-10 dataset for training a hybrid quantum-classical neural network.

Set up the project

Clone the project

Start by cloning the example project:

git clone --depth=1 https://github.com/adap/flower.git _tmp \
        && mv _tmp/examples/quickstart-pennylane . \
        && rm -rf _tmp \
        && cd quickstart-pennylane

This will create a new directory called quickstart-pennylane with the following structure:

quickstart-pennylane
├── quickstart_pennylane
│   ├── __init__.py
│   ├── client_app.py   # Defines your ClientApp
│   ├── server_app.py   # Defines your ServerApp
│   └── task.py         # Defines your model, training and data loading
├── pyproject.toml      # Project metadata like dependencies and configs
└── README.md

Install dependencies and project

Install the dependencies defined in pyproject.toml as well as the quickstart_pennylane package.

pip install -e .

Run the Project

You can run your Flower project in both simulation and deployment mode without making changes to the code. If you are starting with Flower, we recommend you using the simulation mode as it requires fewer components to be launched manually. By default, flwr run will make use of the Simulation Engine.

Run with the Simulation Engine

[!TIP] This example might run slower due to quantum circuit simulation. If your system has a GPU, you can use the local-simulation-gpu federation for better performance. Check the Simulation Engine documentation to learn more.

flwr run .

You can also override some of the settings for your ClientApp and ServerApp defined in pyproject.toml. For example:

flwr run . --run-config "num-server-rounds=5 learning-rate=0.01"

Run the project in the local-simulation-gpu federation that gives CPU and GPU resources to each ClientApp. By default, at most 5xClientApp will run in parallel in the available GPU. You can tweak the degree of parallelism by adjusting the settings of this federation in the pyproject.toml.

# Run with the `local-simulation-gpu` federation
flwr run . local-simulation-gpu

Run with the Deployment Engine

Follow this how-to guide to run the same app in this example but with Flower’s Deployment Engine. After that, you might be intersted in setting up secure TLS-enabled communications and SuperNode authentication in your federation.

If you are already familiar with how the Deployment Engine works, you may want to learn how to run it using Docker. Check out the Flower with Docker documentation.