PyTorch implementation of federated learning framework based on the acceleration of global momentum

Last update: Dec 23, 2021

Related tags

Deep Learning FedAGM

Overview

Federated Learning with Acceleration of Global Momentum

PyTorch implementation of federated learning framework based on the acceleration of global momentum.

Federated Learning with Acceleration of Global Momentum

Geeho Kim, Jinkyu Kim, Bohyung Han

1. Dependencies

This repository is implemented based on PyTorch with Anaconda.

2. Training models

CIFAR-100, 100 clients, Dirichlet (0.3) split, 5% participation

python federated_train.py --cuda_visible_device=1 --method=FedAGM --global_method=FedAGM --config=configs/cifar_actl2.yaml --arch=ResNet18 --weight_decay=1e-3 --gr_clipping_max_norm=10 --alpha=1 --mu=0.001 --gamma=0.9 --momentum=0.0 --tau 1.0 --lr=1e-1 --mode=dirichlet --dirichlet_alpha=0.3  --participation_rate=0.05 --learning_rate_decay 0.995 --set CIFAR100

Owner

GitHub Repository

Toontown House CT Edition

Toontown House: Classic Toontown House Classic source that should just work. ❓ W

5 Jan 09, 2022

The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation

PointNav-VO The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation Project Page | Paper Table of Contents Setup

41 Dec 15, 2022

Soft actor-critic is a deep reinforcement learning framework for training maximum entropy policies in continuous domains.

This repository is no longer maintained. Please use our new Softlearning package instead. Soft Actor-Critic Soft actor-critic is a deep reinforcement

752 Jan 07, 2023

ICLR 2021, Fair Mixup: Fairness via Interpolation

Fair Mixup: Fairness via Interpolation Training classifiers under fairness constraints such as group fairness, regularizes the disparities of predicti

49 Nov 22, 2022

This repository gives an example on how to preprocess the data of the HECKTOR challenge

HECKTOR 2021 challenge This repository gives an example on how to preprocess the data of the HECKTOR challenge. Any other preprocessing is welcomed an

56 Dec 01, 2022

Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"

Memory Efficient Attention Pytorch Implementation of a memory efficient multi-head attention as proposed in the paper, Self-attention Does Not Need O(

180 Jan 05, 2023

PyTorch implementation of federated learning framework based on the acceleration of global momentum

Related tags

Overview

Federated Learning with Acceleration of Global Momentum

1. Dependencies

2. Training models

Owner

Toontown House CT Edition

The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation

Soft actor-critic is a deep reinforcement learning framework for training maximum entropy policies in continuous domains.

ICLR 2021, Fair Mixup: Fairness via Interpolation

This repository gives an example on how to preprocess the data of the HECKTOR challenge

Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"

A curated list of awesome Active Learning

GuideDog is an AI/ML-based mobile app designed to assist the lives of the visually impaired, 100% voice-controlled

A very impractical 3D rendering engine that runs in the python terminal.

Scikit-learn compatible estimation of general graphical models

ThunderGBM: Fast GBDTs and Random Forests on GPUs

SigOpt wrappers for scikit-learn methods

Automatic differentiation with weighted finite-state transducers.

Multimodal commodity image retrieval 多模态商品图像检索

Pytorch Implementation of PointNet and PointNet++++

A tool to analyze leveraged liquidity mining and find optimal option combination for hedging.

Official PyTorch implementation of "ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows"

CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images

A fast, dataset-agnostic, deep visual search engine for digital art history

Graph parsing approach to structured sentiment analysis.