Implementation of the federated dual coordinate descent (FedDCD) method.

Last update: Sep 21, 2022

Related tags

Deep Learning FedDCD.jl

Overview

FedDCD.jl

Implementation of the federated dual coordinate descent (FedDCD) method.

Installation

To install, just call

Pkg.add("https://github.com/ZhenanFanUBC/FedDCD.jl.git")

Get data

We get data from the website of LIBSVM. To download the datasets, just call

mkdir data
cd ./data
wget https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary/rcv1_train.binary.bz2
wget https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary/rcv1_test.binary.bz2
wget https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/mnist.scale.bz2
wget https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/mnist.scale.t.bz2
bzip2 -d rcv1_train.binary.bz2
bzip2 -d rcv1_test.binary.bz2
bzip2 -d mnist.scale.bz2
bzip2 -d mnist.scale.t.bz2

Run FedAvg for toy example.

include("experiments/PrimalMethods.jl")
RunFedAvgAndProx(
    "data/rcv1_train.binary",
    "data/rcv1_train.binary"
    1e-2,
    0.0,
    0.3,
    0.1,
    100,
    "results/toy.txt"
    )

Run FedDCD for toy example.

include("experiments/DualMethods.jl")
RunFedDCD(
    "data/rcv1_train.binary",
    "data/rcv1_train.binary"
    1e-2,
    0.3,
    0.1,
    100,
    "results/toy.txt"
    )

Citing this package

If you use FedDCD.jl for published work, we encourage you to cite the software.

Use the following BibTeX citation:

@article{fan2022dual,
      title={A dual approach for federated learning}, 
      author={Zhenan Fan and Huang Fang and Michael P. Friedlander},
      year={2022},
      eprint={2201.11183},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

Credits

FedDCD.jl is developed by Zhenan Fan and Huang Fang

Implementation of the federated dual coordinate descent (FedDCD) method.

Related tags

Overview

FedDCD.jl

Installation

Get data

Run FedAvg for toy example.

Run FedDCD for toy example.

Citing this package

Credits

Owner

Zhenan Fan

CVPR2021 Workshop - HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization.

Predictive Maintenance LSTM

Object Database for Super Mario Galaxy 1/2.

RCT-ART is an NLP pipeline built with spaCy for converting clinical trial result sentences into tables through jointly extracting intervention, outcome and outcome measure entities and their relations.

Official PyTorch implementation of the paper: Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting.

The fastai book, published as Jupyter Notebooks

ServiceX Transformer that converts flat ROOT ntuples into columnwise data

Code of Adverse Weather Image Translation with Asymmetric and Uncertainty aware GAN

Pytorch implementation of the paper "COAD: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking."

[CVPR'21] FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space

🏅 The Most Comprehensive List of Kaggle Solutions and Ideas 🏅

[NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training

The materials used in the SaxonJS tutorial presented at Declarative Amsterdam, 2021

The project covers common metrics for super-resolution performance evaluation.

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment

GANTheftAuto is a fork of the Nvidia's GameGAN

Code for CPM-2 Pre-Train

Automatic learning-rate scheduler

High-Fidelity Pluralistic Image Completion with Transformers (ICCV 2021)