# FedLab-benchmarks

**Repository Path**: liyupenggg/FedLab-benchmarks

## Basic Information

- **Project Name**: FedLab-benchmarks
- **Description**: Standard implementations of FedLab and its provided benchmarks.
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2022-02-16
- **Last Updated**: 2022-03-09

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

<p align="center"><img src="https://github.com/SMILELab-FL/FedLab/raw/master/docs/imgs/FedLab-logo.svg?raw=True" width=600></p>

# FedLab-benchmarks
This repo contains standard FL algorithm implementations and FL benchmarks using [FedLab](https://github.com/SMILELab-FL/FedLab). 

Currently, following algorithms or benchrmarks are available：

## Optimization Algorithms
- [x] FedAvg: [Communication-Efficient Learning of Deep Networks from Decentralized Data](http://proceedings.mlr.press/v54/mcmahan17a/mcmahan17a.pdf)
- [x] FedAsync: [Asynchronous Federated Optimization](http://arxiv.org/abs/1903.03934)
- [x] FedProx: [Federated Optimization in Heterogeneous Networks](https://arxiv.org/abs/1812.06127)
- [x] FedDyn: [Federated Learning based on Dynamic Regularization](https://openreview.net/pdf?id=B7v4QMR6Z9w)

## Compression Algorithms
- [x] DGC: [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://arxiv.org/abs/1712.01887)
- [x] QSGD: [Communication-Efficient SGD via Gradient Quantization and Encoding](https://proceedings.neurips.cc/paper/2017/hash/6c340f25839e6acdc73414517203f5f0-Abstract.html)

## Datasets
- [x] LEAF: [A Benchmark for Federated Settings](http://arxiv.org/abs/1812.01097)
- [x] NIID-Bench: [Federated Learning on Non-IID Data Silos: An Experimental Study](https://arxiv.org/abs/2102.02079)



## Working list

- [ ] PFL: [Debiasing Model Updates for Improving Personalized Federated Training](http://proceedings.mlr.press/v139/acar21a.html)
- [ ] qFFL: [Fair Resource Allocation in Federated Learning](https://arxiv.org/abs/1905.10497)
- [ ] FedMGDA+: [Federated Learning meets Multi-objective Optimization](https://arxiv.org/abs/2006.11489)

------

**We highly welcome you to contribute federated learning algorithm based on FedLab. If you encounter any problems, do not hesitate to submit an issue or send an email to repo maintainers.**