Starred repositories
HeFlwr: Federated Learning for Heterogeneous Devices
[ICLR 2021] HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
[ICLR2022] Efficient Split-Mix federated learning for in-situ model customization during both training and testing time
A simple code snippet for freezing only part of the layer
Compare neural networks by their feature similarity
The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)
An implementation for the paper "https://arxiv.org/pdf/2003.12795.pdf".
A basic implementation of the classical and split Federated Learning (FL)
37 traditional FL (tFL) or personalized FL (pFL) algorithms, 3 scenarios, and 20 datasets.
A flexible Federated Learning Framework based on PyTorch, simplifying your Federated Learning research.
Convergence Analysis of Sequential Federated Learning on Heterogeneous Data (NeurIPS 2023)
Benchmark of federated learning. Dedicated to the community. 🤗
Exploiting Label Skew in Federated Learning with Model Concatenation (AAAI 2024)
PyTorch code for training neural networks without global back-propagation
Comprehensive and timely academic information on federated learning (papers, frameworks, datasets, tutorials, workshops)
Count the MACs / FLOPs of your PyTorch model.
Official PyTorch implementation of "Speeding up Heterogeneous Federated Learning with Sequentially Trained Superclients", accepted at ICPR 2022
Implementation of paper "Client-Edge-Cloud Hierarchical Federated Learning
Handy PyTorch implementation of Federated Learning (for your painless research)
Code for the following paper
SplitFedLearning using MNIST
Simple Python Socket-based Split Learning technique using PyTorch
This repository includes the official project of SplitAVG, from our paper "SplitAVG: A heterogeneity-aware federated deep learning method for medical imaging".
Releasing the source code Version1.
A PyTorch Implementation of Federated Learning http://doi.org/10.5281/zenodo.4321561