Client Model

Client model research in federated learning focuses on collaboratively training machine learning models across decentralized clients without directly sharing data, aiming to improve model performance and efficiency while preserving privacy. Current research emphasizes addressing data heterogeneity across clients through techniques like cohorting similar clients, adaptive aggregation algorithms, and methods to incorporate information from unlabeled or partially labeled data. This work is significant because it enables the development of robust and accurate models in privacy-sensitive applications, such as healthcare and finance, where data is distributed across multiple institutions or devices.

Papers

November 7, 2022

Closing the Gap between Client and Global Model Performance in Heterogeneous Federated Learning
Hongrui Shi, Valentin Radu, Po Yang
Heterogeneous Federated Learning Global Model Client Collaboration Client Model Heterogeneity Challenge

August 3, 2022

A New Implementation of Federated Learning for Privacy and Security Enhancement
Xiang Ma, Haijian Sun, Rose Qingyang Hu, Yi Qian
Membership Inference Attack Privacy Policy Local Model FedAvg Algorithm Client Model Security Measure

June 18, 2022

Motley: Benchmarking Heterogeneity and Personalization in Federated Learning
Shanshan Wu, Tian Li, Zachary Charles, Yu Xiao, Ziyu Liu, Zheng Xu, Virginia Smith
Transfer Learning Client Model Personalization Method

June 14, 2022

Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring
Zhengquan Luo, Yunlong Wang, Zilei Wang, Zhenan Sun, Tieniu Tan
Domain Specific Convergence Rate Rich Attribute Invariant Feature Diversity Enhancement Client Model Aggregation Function Disentangled Learning

April 17, 2022

Self-Aware Personalized Federated Learning
Huili Chen, Jie Ding, Eric Tramel, Shuang Wu, Anit Kumar Sahu, Salman Avestimehr, Tao Zhang
Uncertainty Quantification Local Model Personalization Performance Client Model Uncertainty Aware Training

April 7, 2022

Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Nan Lu, Zhao Wang, Xiaoxiao Li, Gang Niu, Qi Dou, Masashi Sugiyama
Unsupervised Learning Unlabeled Data Client Model Unsupervised Federated Learning

January 7, 2022

Multi-Model Federated Learning
Neelkamal Bhuyan, Sharayu Moharir
Federated Learning Multiple Model Client Model Single Learning Dexterous Policy