# shaoxiongji/federated-learning

A PyTorch Implementation of Federated Learning

Repository: https://github.com/shaoxiongji/federated-learning
Canonical: https://ross.abutalabs.com/products/federated-learning
Homepage: http://doi.org/10.5281/zenodo.4321561
Language: Python
License: MIT
License Family: permissive
Topics: federated-learning, deep-learning, pytorch
Last push: 2024-07-25T10:13:30+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3078, "days_push": 769, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1515, forks 392 (observed 2026-08-28T04:04:56.486354+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, privacy
- platform: python
- tags: federated-learning, fedavg, pytorch, research-code, mnist, cifar10, non-iid, gpu

## Member repositories
- shaoxiongji/federated-learning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:56.486354+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:32:10.472496+00:00, confidence not recorded.
  - readme: https://github.com/shaoxiongji/federated-learning (fetched 2026-08-28T04:04:56.486354+00:00, sha 65e865664cb5)
  - homepage: http://doi.org/10.5281/zenodo.4321561 (fetched 2026-08-29T11:35:52.592785+00:00, sha 21a1df0173e5)
  - site_page: https://about.zenodo.org (fetched 2026-08-29T11:35:52.602003+00:00, sha 256786d98d3a)
  - site_page: https://support.zenodo.org/help (fetched 2026-08-29T11:35:52.604288+00:00, sha 9a3e6b498d45)
- Data as of 2026-08-30T08:39:29.467469+00:00.