FedAvg Algorithm

Federated Averaging (FedAvg) is a core algorithm in federated learning, aiming to collaboratively train a shared machine learning model across multiple decentralized devices without directly sharing their data. Current research focuses on improving FedAvg's robustness to non-independent and identically distributed (non-IID) data, mitigating communication overhead through techniques like model compression and efficient aggregation strategies (e.g., FedAvgM, FedProx), and addressing challenges like client dropout and Byzantine attacks. These advancements enhance the privacy and efficiency of federated learning, impacting diverse applications ranging from IoT security to personalized healthcare.

Papers

October 7, 2024

Aiding Global Convergence in Federated Learning via Local Perturbation and Mutual Similarity Information
Emanuel Buttaci, Giuseppe Carlo Calafiore
Global Convergence Client Selection Gradient Based Optimization Additive Perturbation FedAvg Algorithm

September 17, 2024

Federated Learning with Integrated Sensing, Communication, and Computation: Frameworks and Performance Analysis
Yipeng Liang, Qimei Chen, Hao Jiang
New Framework Computation Method Performance Analysis FedAvg Algorithm FedAvg Converges Integrated Sensing FL Framework

August 28, 2024

Convergent Differential Privacy Analysis for General Federated Learning: the $f$-DP Perspective
Yan Sun, Li Shen, Dacheng Tao
Differential Privacy Federated Learning Privacy Analysis FedAvg Algorithm FedProx Algorithm

July 31, 2024

FedBChain: A Blockchain-enabled Federated Learning Framework for Improving DeepConvLSTM with Comparative Strategy Insights
Gaoxuan Li, Chern Hong Lim, Qiyao Ma, Xinyu Tang, Hwa Hui Tew, Fan Ding, Xuewen Luo
Federated Learning FedAvg Algorithm ConvLSTM Network

June 18, 2024

Training Diffusion Models with Federated Learning
Matthijs de Goede, Bart Cox, Jérémie Decouchant
Diffusion Model Denoising Diffusion Model Federated Averaging FedAvg Algorithm Diffusion Based Model

March 16, 2024

Enhancing IoT Security Against DDoS Attacks through Federated Learning
Ghazaleh Shirvani, Saeid Ghasemshirazi, Mohammad Ali Alipour
Internet of Thing FedAvg Algorithm

December 24, 2023

FedDMF: Privacy-Preserving User Attribute Prediction using Deep Matrix Factorization
Ming Cheung
Matrix Factorization FedAvg Algorithm Attribute Prediction User Attribute User Data

December 12, 2023

Privacy-Aware Energy Consumption Modeling of Connected Battery Electric Vehicles using Federated Learning
Sen Yan, Hongyuan Fang, Ji Li, Tomas Ward, Noel O'Connor, Mingming Liu
Energy Consumption FedAvg Algorithm Connected Vehicle Vehicle Energy Consumption

November 21, 2023

FedDRO: Federated Compositional Optimization for Distributionally Robust Learning
Prashant Khanduri, Chengyin Li, Rafi Ibn Sultan, Yao Qiang, Joerg Kliewer, Dongxiao Zhu
Federated Learning Distributionally Robust FedAvg Algorithm Compositional Optimization Compositional Operation

October 16, 2023

Over-the-Air Federated Learning and Optimization
Jingyang Zhu, Yuanming Shi, Yong Zhou, Chunxiao Jiang, Wei Chen, Khaled B. Letaief
Optimization Purpose Convergence Guarantee Air Federated Learning Air Computation FedAvg Algorithm

September 3, 2023

A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Data
Hamza Reguieg, Mohammed El Hanjri, Mohamed El Kamili, Abdellatif Kobbane
Model Training Data Heterogeneity Heterogeneous Data Federated Averaging Comparative Evaluation FedAvg Algorithm FedAvg Converges Ordered Matrix Dirichlet

August 23, 2023

Unsupervised anomalies detection in IIoT edge devices networks using federated learning
Niyomukiza Thamar, Hossam Samy Elsaid Sharara
Unsupervised Anomaly Detection Federated Prompt Cooperation Internet of Thing Network FedAvg Algorithm FedAvg Converges

July 20, 2023

Boosting Federated Learning Convergence with Prototype Regularization
Yu Qiao, Huy Q. Le, Choong Seon Hong
Heterogeneous Data FedAvg Algorithm Prototype Based Regularization Global Prototype Performance Guaranteed Regularization

June 26, 2023

Federated Learning on Non-iid Data via Local and Global Distillation
Xiaolin Zheng, Senci Ying, Fei Zheng, Jianwei Yin, Longfei Zheng, Chaochao Chen, Fengqin Dong
Knowledge Distillation Self Distillation FedAvg Algorithm Non IID Data Global Distillation

June 21, 2023

MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updates
Yuchang Sun, Yuyi Mao, Jun Zhang
Loss Function Pre Change Information FedAvg Algorithm Novel Mimic Algorithm Stable Convergence Client Dropout

May 8, 2023

Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts
Kun Jin, Tongxin Yin, Zhongzhu Chen, Zeyu Sun, Xueru Zhang, Yang Liu, Mingyan Liu
Federated Learning Distribution Shift Solution Path FedAvg Algorithm Performative Prediction Data Distribution Shift Stable Optimization

March 31, 2023

Benchmarking FedAvg and FedCurv for Image Classification Tasks
Bruno Casella, Roberto Esposito, Carlo Cavazzoni, Marco Aldinucci
Image Classification Task FedAvg Algorithm Data Lake Federated Learning Algorithm

February 21, 2023

CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled Regularization
Nang Hung Nguyen, Duc Long Nguyen, Trong Bang Nguyen, Thanh-Hung Nguyen, Huy Hieu Pham, Truong Thao Nguyen, Phi Le Nguyen
Raw Data FedAvg Algorithm Non IID Data Skewed Non IID Two Stage Aggregation

February 13, 2023

FedDA: Faster Framework of Local Adaptive Gradient Methods via Restarted Dual Averaging
Junyi Li, Feihu Huang, Heng Huang
Federated Learning Learning Rate FedAvg Algorithm Adaptive Gradient Method Faster Model Dual Averaging

February 7, 2023

Federated Learning with Regularized Client Participation
Grigory Malinovsky, Samuel Horváth, Konstantin Burlachenko, Peter Richtárik
Convergence Rate FedAvg Algorithm Client Sampling Client Participation

FedAvg Algorithm

Papers

Aiding Global Convergence in Federated Learning via Local Perturbation and Mutual Similarity Information

Federated Learning with Integrated Sensing, Communication, and Computation: Frameworks and Performance Analysis

Convergent Differential Privacy Analysis for General Federated Learning: the $f$-DP Perspective

FedBChain: A Blockchain-enabled Federated Learning Framework for Improving DeepConvLSTM with Comparative Strategy Insights

Training Diffusion Models with Federated Learning

Enhancing IoT Security Against DDoS Attacks through Federated Learning

FedDMF: Privacy-Preserving User Attribute Prediction using Deep Matrix Factorization

Privacy-Aware Energy Consumption Modeling of Connected Battery Electric Vehicles using Federated Learning

FedDRO: Federated Compositional Optimization for Distributionally Robust Learning

Over-the-Air Federated Learning and Optimization

A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Data

Unsupervised anomalies detection in IIoT edge devices networks using federated learning

Boosting Federated Learning Convergence with Prototype Regularization

Federated Learning on Non-iid Data via Local and Global Distillation

MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updates

Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts

Benchmarking FedAvg and FedCurv for Image Classification Tasks

CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled Regularization

FedDA: Faster Framework of Local Adaptive Gradient Methods via Restarted Dual Averaging

Federated Learning with Regularized Client Participation