pFL Method

Personalized Federated Learning (pFL) is a machine learning approach that addresses the heterogeneity of data across multiple clients in a privacy-preserving manner, aiming to train personalized models while maintaining some level of global model consistency. Current research focuses on improving the efficiency and robustness of pFL algorithms, including exploring various model architectures and addressing challenges like non-IID data, communication costs, and backdoor attacks. This field is significant because it enables the development of more accurate and adaptable AI systems while respecting data privacy, with potential applications in diverse areas such as healthcare and personalized recommendations. The development of comprehensive benchmark datasets and algorithm libraries is also a key area of current focus.

Papers

October 18, 2024

Personalizing Low-Rank Bayesian Neural Networks Via Federated Learning
Boning Zhang, Dongzhu Liu, Osvaldo Simeone, Guanchu Wang, Dimitrios Pezaros, Guangxu Zhu
Uncertainty Quantification Personalized Federated Learning Confidence Estimation pFL Method

July 4, 2024

10 Years of Fair Representations: Challenges and Opportunities
Mattia Cerrato, Marius Köppel, Philipp Wolf, Stefan Kramer
Technical Challenge Emerging Opportunity Last Decade Fair Representation Neural Network Representation Deep Learning Theory Fair Representation Learning pFL Method

June 28, 2024

Personalized Interpretation on Federated Learning: A Virtual Concepts approach
Peng Yan, Guodong Long, Jing Jiang, Michael Blumenstein
Federated Learning Interpretable Concept pFL Method Concept Based Approach

June 17, 2024

Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offs
Haifeng Wen, Hong Xing, Osvaldo Simeone
Strong Generalization Fine Tuning Pre Training Generalization Performance Air Federated Learning Training Paradigm Optimal Generalization pFL Method

April 18, 2024

One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity
Naibo Wang, Yuchen Deng, Wenjie Feng, Shichen Fan, Jianwei Yin, See-Kiong Ng
Federated Learning Raw Data Diverse Model Simple Pooling pFL Method

February 16, 2024

Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants
Peter Richtárik, Elnur Gasanov, Konstantin Burlachenko
Stochastic Gradient Error Feedback Communication Complexity Convergence Performance pFL Method Quadratic Number

January 22, 2024

Personalized Over-the-Air Federated Learning with Personalized Reconfigurable Intelligent Surfaces
Jiayu Mao, Aylin Yener
Multi Task Learning Air Federated Learning Reconfigurable Intelligent Surface pFL Method Personalization Task

December 8, 2023

PFLlib: Personalized Federated Learning Algorithm Library
Jianqing Zhang, Yang Liu, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Jian Cao
Federated Learning Personalized Federated Learning pFL Method

August 20, 2023

GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning
Jianqing Zhang, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Jian Cao, Haibing Guan
World Event Personalized Federated Learning pFL Method Personalization System

July 29, 2023

You Can Backdoor Personalized Federated Learning
Tiandi Ye, Cen Chen, Yinggui Wang, Xiang Li, Ming Gao
Backdoor Attack Malicious Client Step Attack pFL Method Decoupling Degradation

April 2, 2023

Personalized Federated Learning with Local Attention
Sicong Liang, Junchao Tian, Shujun Yang, Yu Zhang
Personalized Federated Learning Local Context pFL Method Heterogeneous Label Personalized Attention

February 13, 2023

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
Chulin Xie, De-An Huang, Wenda Chu, Daguang Xu, Chaowei Xiao, Bo Li, Anima Anandkumar
Personalized Federated Learning Generalization Guarantee pFL Method Better Out of Distribution Generalization

November 19, 2022

Personalized Federated Learning with Hidden Information on Personalized Prior
Mingjia Shi, Yuhao Zhou, Qing Ye, Jiancheng Lv
Personalized Federated Learning Bayesian Learning Hidden Knowledge Bregman Divergence Privacy Preserving Training pFL Method Personalized Prior

June 8, 2022

pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning
Daoyuan Chen, Dawei Gao, Weirui Kuang, Yaliang Li, Bolin Ding
Personalized Federated Learning Comprehensive Benchmark pFL Method

March 7, 2022

State space partitioning based on constrained spectral clustering for block particle filtering
Rui Min, Christelle Garnier, François Septier, John Klein
State Space Spectral Clustering Particle Filter Constrained Clustering pFL Method State Vector