Client Data

Client data in federated learning (FL) research focuses on efficiently training machine learning models across decentralized datasets while preserving data privacy. Current efforts concentrate on addressing data heterogeneity through techniques like federated averaging, diffusion models for data augmentation and synthesis, and novel clustering methods to group clients with similar data distributions. These advancements aim to improve model accuracy and training efficiency in diverse scenarios, impacting fields like medical imaging and communication systems by enabling collaborative model training without compromising sensitive information.

Papers

November 12, 2024

Dual-Criterion Model Aggregation in Federated Learning: Balancing Data Quantity and Quality
Haizhou Zhang, Xianjia Yu, Tomi Westerlund
Quality Issue Data Aggregation Model Aggregation Quantity Aware Aggregation Method Data Balancing Client Data

June 17, 2024

Feasibility of Federated Learning from Client Databases with Different Brain Diseases and MRI Modalities
Felix Wagner, Wentian Xu, Pramit Saha, Ziyun Liang, Daniel Whitehouse, David Menon, Virginia Newcombe, Natalie Voets, J. Alison Noble, Konstantinos Kamnitsas
Segmentation Model Magnetic Resonance Imaging Task Feasibility Client Data Different Brain

November 15, 2023

One-Shot Federated Learning with Classifier-Guided Diffusion Models
Mingzhao Yang, Shangchao Su, Bin Li, Xiangyang Xue
Pre Trained Diffusion Model Centralized Training Client Data Training Data Generator Classifier Guided Diffusion

October 20, 2023

An Efficient Federated Learning Framework for Training Semantic Communication System
Loc X. Nguyen, Huy Q. Le, Ye Lin Tun, Pyae Sone Aung, Yan Kyaw Tun, Zhu Han, Choong Seon Hong
Federated Learning Semantic Communication State of the Art Deep Semantic Communication System Resource Constrained Device Centralized Training Client Data

May 6, 2023

Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model
Mingzhao Yang, Shangchao Su, Bin Li, Xiangyang Xue
Diffusion Model Semi Supervised Pre Trained Diffusion Model Centralized Training Co Training One Shot Federated Learning Client Data

September 30, 2022

Federated Training of Dual Encoding Models on Small Non-IID Client Datasets
Raviteja Vemulapalli, Warren Richard Morningstar, Philip Andrew Mansfield, Hubert Eichner, Karan Singhal, Arash Afkanpour, Bradley Green
Representation Learning Loss Function Centralized Training Small Scale Federated Training Client Data

September 21, 2022

Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces
Saeed Vahidian, Mahdi Morafah, Weijia Wang, Vyacheslav Kungurtsev, Chen Chen, Mubarak Shah, Bill Lin
Clustered Federated Learning Truncated Singular Value Decomposition Similarity Distribution Client Data

February 1, 2022

Factorized-FL: Agnostic Personalized Federated Learning with Kernel Factorization & Similarity Matching
Wonyong Jeong, Sung Ju Hwang
Personalized Federated Learning Heterogeneous Domain Client Data Kernel Matrix Factorization

January 5, 2022

FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients
Jaemin Shin, Yuanchun Li, Yunxin Liu, Sung-Ju Lee
Federated Learning Raw Data Centralized Training Heterogeneous Client Pace Adaptive Client Data

Client Data

Papers

Dual-Criterion Model Aggregation in Federated Learning: Balancing Data Quantity and Quality

Feasibility of Federated Learning from Client Databases with Different Brain Diseases and MRI Modalities

One-Shot Federated Learning with Classifier-Guided Diffusion Models

An Efficient Federated Learning Framework for Training Semantic Communication System

Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model

Federated Training of Dual Encoding Models on Small Non-IID Client Datasets

Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces

Factorized-FL: Agnostic Personalized Federated Learning with Kernel Factorization & Similarity Matching

FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients