Migration of Edge-based Distributed Federated Learning

Related tags

Deep LearningFedFly
Overview

FedFly: Towards Migration in Edge-based Distributed Federated Learning

About the research

Due to mobility, a device participating in Federated Learning (FL) may disconnect from one edge server and will need to connect to another edge server during FL training. This becomes more challenging when a Deep Neural Network (DNN) is partitioned between device and edge server referred to as edge-based FL. Moving a device without migrating the accompanying training data from a source edge server to the destination edge server will result in training for the device having to start all over again on the destination server. This will in turn affect the performance of edge-based FL and result in large training times. FedFly addresses the mobility challenge of devices in edge-based distributed FL. This research designs, develops and implements the technique for migrating DNN in the context of edge-based distributed FL.

FedFly is implemented and evaluated in a hierarchical cloud-edge-device architecture on a lab-based testbed to validate the migration technique of edge-based FL. The testbed that includes four IoT devices, two edge servers, and one central server (cloud-like) running the VGG-5 DNN model. The empirical findings uphold and validates our claims in terms of training time and accuracy using balanced and imbalanced datasets when compared to state-of-the-art approaches, such as SplitFed. FedFly has a negligible overhead of up to 2 seconds but saves a significant amount of training time while maintaining accuracy.

FedFly System width=

More information on the steps in relation to distributed FL and the mobility of devices within the FedFly system are presented in the research article entitled, "FedFly: Towards Migration in Edge-based Distributed Federated Learning".

Code Structure

The repository contains the source code of FedFly. The overall architecture is divided as follows:

  1. Central server (Central server, such as a cloud location, for running the FedAverage algorithm)
  2. Edge servers (separated as Source and Destination for migration)
  3. Devices

The repository also arranges the code according to the above described architecture.

The results are saved as pickle files in the results folder on the Central Server.

Currently, CIFAR10 dataset and Convolutional Neural Network (CNN) models are supported. The code can be extended to support other datasets and models.

Setting up the environment

The code is tested on Python 3 with Pytorch version 1.4 and torchvision 0.5.

In order to test the code, install Pytorch and torchvision on each IoT device (for example, Raspberry Pis as used in this work). One can install from pre-built PyTorch and torchvision pip wheel. Download respective pip wheel as follows:

Or visit https://github.com/Rehmatkhan/InstallPytrochScript and follow the simple steps:

# install and configure pytorch and torchvision on Raspberry devices
#move to sudo
sudo -i
#update
apt update
apt install git
git clone https://github.com/Rehmatkhan/InstallPytrochScript.git
mv InstallPytrochScript/install_python_pytorch.sh .
chmod +x install_python_pytorch.sh
rm -rf InstallPytrochScript
./install_python_pytorch.sh

All configuration options are given in config.py at the central server, which contains the architecture, model, and FL training hyperparameters. Therefore, modify the respective hostname and ip address in config.py. CLIENTS_CONFIG and CLIENTS_LIST in config.py are used for indexing and sorting. Note that config.py file must be changed at the source edge server, destination edge server and at each device.

# Network configration
SERVER_ADDR= '192.168.10.193'
SERVER_PORT = 51000
UNIT_MODEL_SERVER = '192.168.10.102'
UNIT_PORT = 51004

EDGE_SERVERS = {'Sierra.local': '192.168.10.193', 'Rehmats-MacBook-Pro.local':'192.168.10.154'}


K = 4 # Number of devices

# Unique clients order
HOST2IP = {'raspberrypi3-1':'192.168.10.93', 'raspberrypi3-2':'192.168.10.31', 'raspberrypi4-1': '192.168.10.169', 'raspberrypi4-2': '192.168.10.116'}
CLIENTS_CONFIG= {'192.168.10.93':0, '192.168.10.31':1, '192.168.10.169':2, '192.168.10.116':3 }
CLIENTS_LIST= ['192.168.10.93', '192.168.10.31', '192.168.10.169', '192.168.10.116'] 

Finally, download the CIFAR10 datasets manually and put them into the datasets/CIFAR10 folder (python version).

To test the code:

Launch FedFly central server

python FedFly_serverrun.py --offload True #FedFly training

Launch FedFly source edge server

python FedFly_serverrun.py --offload True #FedFly training

Launch FedFly destination edge server

python FedFly_serverrun.py --offload True #FedFly training

Launch FedFly devices

python FedFly_clientrun.py --offload True #FedFly training

Citation

Please cite the paper as follows: Rehmat Ullah, Di Wu, Paul Harvey, Peter Kilpatrick, Ivor Spence and Blesson Varghese, "FedFly: Towards Migration in Edge-based Distributed Federated Learning", 2021.

@misc{ullah2021fedfly,
      title={FedFly: Towards Migration in Edge-based Distributed Federated Learning}, 
      author={Rehmat Ullah and Di Wu and Paul Harvey and Peter Kilpatrick and Ivor Spence and Blesson Varghese},
      year={2021},
      eprint={2111.01516},
      archivePrefix={arXiv},
      primaryClass={cs.DC}
}
Owner
qub-blesson
qub-blesson
PAMI stands for PAttern MIning. It constitutes several pattern mining algorithms to discover interesting patterns in transactional/temporal/spatiotemporal databases

Introduction PAMI stands for PAttern MIning. It constitutes several pattern mining algorithms to discover interesting patterns in transactional/tempor

RAGE UDAY KIRAN 43 Jan 08, 2023
Code for our CVPR 2022 Paper "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection"

GEN-VLKT Code for our CVPR 2022 paper "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection". Contributed by Yue Lia

Yue Liao 47 Dec 04, 2022
Python scripts form performing stereo depth estimation using the CoEx model in ONNX.

ONNX-CoEx-Stereo-Depth-estimation Python scripts form performing stereo depth estimation using the CoEx model in ONNX. Stereo depth estimation on the

Ibai Gorordo 8 Dec 29, 2022
nnFormer: Interleaved Transformer for Volumetric Segmentation

nnFormer: Interleaved Transformer for Volumetric Segmentation Code for paper "nnFormer: Interleaved Transformer for Volumetric Segmentation ". Please

jsguo 610 Dec 28, 2022
Implementation of ConvMixer-Patches Are All You Need? in TensorFlow and Keras

Patches Are All You Need? - ConvMixer ConvMixer, an extremely simple model that is similar in spirit to the ViT and the even-more-basic MLP-Mixer in t

Sayan Nath 8 Oct 03, 2022
Code implementation for the paper 'Conditional Gaussian PAC-Bayes'.

CondGauss This repository contains PyTorch code for the paper Stochastic Gaussian PAC-Bayes. A novel PAC-Bayesian training method is implemented. Ther

0 Nov 01, 2021
All the code and files related to the MI-Lab of UE19CS305 course in sem 5

Machine-Intelligence-Lab-CS305 The compilation of all the code an drelated files from MI-Lab UE19CS305 (of batch 2019-2023) offered by PES University

Arvind Krishna 3 Nov 10, 2022
Hcpy - Interface with Home Connect appliances in Python

Interface with Home Connect appliances in Python This is a very, very beta inter

Trammell Hudson 116 Dec 27, 2022
License Plate Detection Application

LicensePlate_Project πŸš— πŸš™ [Project] 2021.02 ~ 2021.09 License Plate Detection Application Overview 1. 데이터 μˆ˜μ§‘ 및 라벨링 μ°¨λŸ‰ 번호판 이미지λ₯Ό 직접 μˆ˜μ§‘ν•˜μ—¬ 각 이미지에 λŒ€ν•΄ '번호판

4 Oct 10, 2022
Code for CVPR2019 Towards Natural and Accurate Future Motion Prediction of Humans and Animals

Motion prediction with Hierarchical Motion Recurrent Network Introduction This work concerns motion prediction of articulate objects such as human, fi

Shuang Wu 85 Dec 11, 2022
Visualization toolkit for neural networks in PyTorch! Demo -->

FlashTorch A Python visualization toolkit, built with PyTorch, for neural networks in PyTorch. Neural networks are often described as "black box". The

Misa Ogura 692 Dec 29, 2022
Cave Generation using metaballs in Blender. Originally created by sdfgeoff, Edited by Myself (Archie Jaskowicz).

Blender-Cave-Generation Cave Generation using metaballs in Blender. Originally created by sdfgeoff, Edited by Myself (Archie Jaskowicz). Installation

2 Dec 28, 2022
Compares various time-series feature sets on computational performance, within-set structure, and between-set relationships.

feature-set-comp Compares various time-series feature sets on computational performance, within-set structure, and between-set relationships. Reposito

Trent Henderson 7 May 25, 2022
The final project of "Applying AI to 3D Medical Imaging Data" from "AI for Healthcare" nanodegree - Udacity.

Quantifying Hippocampus Volume for Alzheimer's Progression Background Alzheimer's disease (AD) is a progressive neurodegenerative disorder that result

Omar Laham 1 Jan 14, 2022
Earth Vision Foundation

EVer - A Library for Earth Vision Researcher EVer is a Pytorch-based Python library to simplify the training and inference of the deep learning model.

Zhuo Zheng 34 Nov 26, 2022
Official implementation of our paper "LLA: Loss-aware Label Assignment for Dense Pedestrian Detection" in Pytorch.

LLA: Loss-aware Label Assignment for Dense Pedestrian Detection This project provides an implementation for "LLA: Loss-aware Label Assignment for Dens

35 Dec 06, 2022
[CVPR 2020] Interpreting the Latent Space of GANs for Semantic Face Editing

InterFaceGAN - Interpreting the Latent Space of GANs for Semantic Face Editing Figure: High-quality facial attributes editing results with InterFaceGA

GenForce: May Generative Force Be with You 1.3k Dec 29, 2022
Code for Deep Single-image Portrait Image Relighting

Deep Single-Image Portrait Relighting [Project Page] Hao Zhou, Sunil Hadap, Kalyan Sunkavalli, David W. Jacobs. In ICCV, 2019 Overview Test script for

438 Jan 05, 2023
Outlier Exposure with Confidence Control for Out-of-Distribution Detection

OOD-detection-using-OECC This repository contains the essential code for the paper Outlier Exposure with Confidence Control for Out-of-Distribution De

Nazim Shaikh 64 Nov 02, 2022
SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data Au

14 Nov 28, 2022