communication-efficiency

FedML - The Research and Production Integrated Federated Learning Library: https://fedml.ai

All materials you need for Federated Learning: blogs, videos, papers, and softwares, etc.

🏆 Official implementation of LangCoop: Collaborative Driving with Natural Language

Paper list of federated learning: About system design

FedAnil+ is a novel lightweight, and secure Federated Deep Learning Model to address non-IID data, privacy concerns, and communication overhead. This repo hosts a simulation for FedAnil+ written in Python.

The communication efficiency of federated learning is improved by sparsifying the parameters uploaded by the clients.

Communication-Efficient Federated Learning via Transferring Codebooks

This project implements communication-efficient online federated learning strategies for resource-constrained devices using random Fourier features (RFFs) for kernel regression. It reduces communication overhead through partial-sharing and event-triggered updates, ensuring efficient local model updates.

Federated Dropout with transfer learning. Clients train reduced submodels to cut communication cost, trading a little accuracy for much smaller updates.

Hybrid Federated Learning with Structured Model Pruning and Gradient Sparsification on MNIST

Communication-Efficient Federated Learning via Transferring Codebooks

This work is a journal paper published at The Journal of Supercomputing in 2023, focusing on improving communication efficiency of a distributed learning system using age-based worker selection techniques.

图增强联邦推荐：Top-k 稀疏上传 + 误差反馈 + 自适应聚类 + 簇内图聚合；单轮上传开销较最优基线降低约 88.6%。已被《小型微型计算机系统》录用。

This repository implements a communication-efficient online federated learning framework for nonlinear regression using partial sharing. Clients update local models with streaming data and share only portions of those updates with the server, reducing communication overhead while maintaining performance.

Communication-efficient federated learning through adaptive weight clustering and server-side distillation.