CVPR 2024 accepted paper, An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
-
Updated
Mar 12, 2025 - Python
8000
CVPR 2024 accepted paper, An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
AAAI 2024 accepted paper, FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
KDD 2023 accepted paper, FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
NeurIPS 2023 accepted paper, Eliminating Domain Bias for Federated Learning in Representation Space
ICCV 2023 accepted paper, GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning
FedAnil is a secure blockchain-enabled Federated Deep Learning Model to address non-IID data and privacy concerns. This repo hosts a simulation for FedAnil written in Python.
testing adhocSL
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.
FedAnil++ is a Privacy-Preserving and Communication-Efficient Federated Deep Learning Model to address non-IID data, privacy concerns, and communication overhead. This repo hosts a simulation for FedAnil++ written in Python.
This repository is PyTorch implementation for paper CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled Regularization which is accepted by CCGRID-23 Conference.
This is the PyTorch implementation of our paper "Jie Du, Wei Li, Peng Liu, et al. Model projection based Federated Learning for Non-IID data" .
a semi-synchronous Federated Learning method (LESSON) for hetrogenous wireless clients with non-iid data distribution
Generate and download free synthetic datasets instantly! A Streamlit app with built-in statistical validation tools like Chi-Square and Mutual Information.
Robust benchmarking of FedAvg, SCAFFOLD, FedGH & FedSAM on non-IID MNIST using Dirichlet-based client splits.
The provided Python script generates non-IID (non-identically independently distributed) datasets for use in federated learning simulations. Federated learning often requires data partitions to simulate real-world scenarios where data across devices or clients is unevenly distributed.
The project aims to explore Federated Learning in scenarios with non-IID data (non-Independent and Identically Distributed) for the task of movie recommendation.
This project simulates a Federated Learning system using non-IID MNIST data across multiple clients, focusing on collaborative training without data sharing. It tracks performance metrics like global accuracy, validation loss, and fairness while allowing each client to personalize the global model locally.
Add a description, image, and links to the non-iid-data topic page so that developers can more easily learn about it.
To associate your repository with the non-iid-data topic, visit your repo's landing page and select "manage topics."