# AshwinRJ/Federated-Learning-PyTorch

Implementation of Communication-Efficient Learning of Deep Networks from Decentralized Data

Repository: https://github.com/AshwinRJ/Federated-Learning-PyTorch
Canonical: https://ross.abutalabs.com/products/federated-learning-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: federated-learning, distributed-computing, deep-learning, pytorch, python
Last push: 2024-05-07T14:34:34+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2847, "days_push": 848, "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 1437, forks 461 (observed 2026-08-28T04:04:43.802291+00:00)

## What it is
A PyTorch implementation of the FedAvg algorithm from the paper 'Communication-Efficient Learning of Deep Networks from Decentralized Data'. It provides baseline and federated training scripts for simple MLP and CNN models on MNIST, Fashion MNIST, and CIFAR10 under IID and non-IID data distributions.

## Use cases
- reproduce the FedAvg federated learning paper
- simulate federated learning with IID and non-IID data splits
- train a global model across many simulated local clients
- experiment with different numbers of users and local epochs in federated training
- learn how federated averaging works in PyTorch
- benchmark federated vs centralized training on MNIST and CIFAR

## When to choose
- you want a minimal, readable reference implementation of FedAvg
- you need to run quick federated learning experiments on small image datasets
- you are teaching or learning the basics of federated learning

## When to avoid
- you need production federated learning with real distributed clients and secure aggregation
- you require large-scale models, differential privacy, or communication compression
- you need actively maintained code with broad dataset and model support

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, microservices, developer-tools
- platform: python, cross-platform
- tags: federated-learning, pytorch, research-code, fedavg, non-iid, mnist, cifar, gpu

## Member repositories
- AshwinRJ/Federated-Learning-PyTorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:43.802291+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 2026-08-30T04:36:42.504834+00:00, confidence not recorded.
  - readme: https://github.com/AshwinRJ/Federated-Learning-PyTorch (fetched 2026-08-28T04:04:43.802291+00:00, sha c0bfc58f417c)
- Data as of 2026-08-30T08:39:29.467469+00:00.