shaoxiongji/federated-learning

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1515 stars · 392 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch implementation of the FedAvg federated learning algorithm reproducing the McMahan et al. AISTATS 2017 paper. It includes experiments on MNIST and CIFAR-10 in both IID and non-IID settings with MLP and CNN models.

Use cases

• reproduce the FedAvg federated learning paper
• run federated averaging experiments on MNIST and CIFAR-10
• learn how federated learning works with a minimal PyTorch example
• compare IID vs non-IID training in federated settings
• get a citable baseline implementation of federated learning

When to choose

• you want a small, readable reference implementation of FedAvg for research or teaching
• you need a citable baseline (Zenodo DOI) for federated learning experiments on MNIST/CIFAR-10

When to avoid

• you need a production or scalable federated learning framework with real distributed clients
• you require parallel computing, advanced FL algorithms (FedProx, SCAFFOLD), or other datasets
• you need actively maintained code with recent PyTorch compatibility

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning privacy python federated-learning fedavg pytorch research-code mnist cifar10 non-iid gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="shaoxiongji/federated-learning")