Clustered Federated Learning

Clustered Federated Learning (CFL) aims to improve the efficiency and accuracy of federated learning by grouping clients with similar data distributions into clusters, allowing for more effective model training within each cluster. Current research focuses on developing adaptive clustering algorithms that dynamically determine the optimal number of clusters and integrate global and local knowledge effectively, often employing techniques like dimensionality reduction, gradient similarity analysis, and consensus-based optimization. This approach addresses the significant challenge of data heterogeneity in federated learning, leading to improved model performance and enhanced privacy preservation in various applications, particularly in healthcare and distributed edge computing.

Papers

November 3, 2024

Federated Learning Clients Clustering with Adaptation to Data Drifts
Minghao Li (1), Dmitrii Avdiukhin (2), Rana Shahout (1), Nikita Ivkin (3), Vladimir Braverman (4), Minlan Yu (1) ((1) Harvard University, (2) Northwestern University, (3) Amazon, (4) Rice University)
Adaptation Concern Data Drift Client Heterogeneity Clustered Federated Learning Adaptive Clustering Federated Learning Client

October 9, 2024

Distributionally Robust Clustered Federated Learning: A Case Study in Healthcare
Xenia Konti, Hans Riess, Manos Giannopoulos, Yi Shen, Michael J. Pencina, Nicoleta J. Economou-Zavlanos, Michael M. Zavlanos
Case Study Federated Learning Healthcare System Heterogeneous Data Robust Clustering Clustered Federated Learning Client Data Heterogeneity

October 4, 2024

Deep Domain Isolation and Sample Clustered Federated Learning for Semantic Segmentation
Matthis Manthe (LIRIS, CREATIS), Carole Lartizien (MYRIAD), Stefan Duffner (LIRIS)
Semantic Segmentation Domain Discriminator Clustered Federated Learning Label Distribution Shift

March 25, 2024

FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data
Yuxin Zhang, Haoyu Chen, Zheng Lin, Zhe Chen, Jin Zhao
Heterogeneous Data Layer Wise Clustered Federated Learning

March 10, 2024

Analysis of Total Variation Minimization for Clustered Federated Learning
A. Jung
General Analysis Total Variation Statistical Heterogeneity Clustered Federated Learning

November 22, 2023

A Joint Gradient and Loss Based Clustered Federated Learning Design
Licheng Lin, Mingzhe Chen, Zhaohui Yang, Yusen Wu, Yuchen Liu
Joint Optimization Interest Loss Local Model Clustered Federated Learning FL Algorithm Efficient Clustering

October 9, 2023

Find Your Optimal Assignments On-the-fly: A Holistic Framework for Clustered Federated Learning
Yongxin Guo, Xiaoying Tang, Tao Lin
Data Heterogeneity Client Heterogeneity Clustered Federated Learning Clustering Framework Optimal Assignment

September 4, 2023

Federated cINN Clustering for Accurate Clustered Federated Learning
Yuhao Zhou, Minjia Shi, Yuxin Tian, Yuanxi Li, Qing Ye, Jiancheng Lv
Clustered Federated Learning Federated Foundation Model Crowd Intelligence

July 17, 2023

Privacy-preserving patient clustering for personalized federated learning
Ahmed Elhussein, Gamze Gursoy
LeArning Abstract Patient Data Federated Machine Learning Clustered Federated Learning Patient Level

May 4, 2023

FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization
Jose A. Carrillo, Nicolas Garcia Trillos, Sixu Li, Yuhua Zhu
Mean Field New Algorithm Clustered Federated Learning Consensus Based Optimization

December 25, 2022

Social-Aware Clustered Federated Learning with Customized Privacy Preservation
Yuntao Wang, Zhou Su, Yanghe Pan, Tom H Luan, Ruidong Li, Shui Yu
Differential Privacy Privacy Preservation Clustered Federated Learning

November 8, 2022

Clustered Federated Learning based on Nonconvex Pairwise Fusion
Xue Yu, Ziyi Liu, Wu Wang, Yifan Sun
Convergence Guarantee Pairwise Learning Federated Clustering Clustered Federated Learning

October 20, 2022

An Improved Algorithm for Clustered Federated Learning
Harshvardhan, Avishek Ghosh, Arya Mazumdar
Improved Algorithm Federated Clustering Clustered Federated Learning Clustering Framework Simultaneous Training

October 5, 2022

Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
Donald Shenaj, Eros Fanì, Marco Toldo, Debora Caldarola, Antonio Tavera, Umberto Michieli, Marco Ciccone, Pietro Zanuttigh, Barbara Caputo
LeArning Abstract Semantic Segmentation Pre Trained Model Self Supervision Regularization Technique Domain Name Smart Device Clustered Federated Learning

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

June 13, 2022

Content Popularity Prediction in Fog-RANs: A Clustered Federated Learning Based Approach
Zhiheng Wang, Yanxiang Jiang, Fu-Chun Zheng, Mehdi Bennis, Xiaohu You
Popularity Prediction Clustered Federated Learning Content Popularity

March 23, 2022

Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matching
Zexi Li, Jiaxun Lu, Shuang Luo, Didi Zhu, Yunfeng Shao, Yinchuan Li, Zhimeng Zhang, Yongheng Wang, Chao Wu
Peer to Peer Client Heterogeneity Clustered Federated Learning Order Neighbor Neighbor Correspondence Matching

February 13, 2022

On the Convergence of Clustered Federated Learning
Jie Ma, Guodong Long, Tianyi Zhou, Jing Jiang, Chengqi Zhang
Early Stage Convergence Personalized Model Model Personalization Clustered Federated Learning Personalized Fl

December 11, 2021

FedSoft: Soft Clustered Federated Learning with Proximal Local Updating
Yichen Ruan, Carlee Joe-Wong
Clustered Federated Learning