the latest in aiBeta

Federated Averaging

Federated Averaging (FedAvg) is a machine learning technique enabling collaborative model training across decentralized devices without directly sharing sensitive data. Current research focuses on addressing challenges like data heterogeneity (variations in data distributions across devices) and communication efficiency, often employing techniques such as variance reduction, adaptive learning rates, and novel aggregation methods beyond simple averaging, including generative approaches and model recombination. These advancements aim to improve the accuracy and scalability of FedAvg for diverse applications, particularly in privacy-sensitive domains like healthcare and mobile computing, where data decentralization is crucial.

69papers

Papers

March 13, 2025

PluralLLM: Pluralistic Alignment in LLMs via Federated Learning
Large Language Model Preference Learning Federated Averaging Pluralistic Alignment

March 6, 2025

Privacy Preserving and Robust Aggregation for Cross-Silo Federated Learning in Non-IID Settings
Federated Averaging Privacy Preserving LeArning Abstract Non IID Gradient Update Gradient Masking Robust Aggregation Federated Prompt Cooperation

February 28, 2025

QFAL: Quantum Federated Adversarial Learning
Adversarial Attack Adversarial Learning Quantum Neural Network Quantum Federated Learning Federated Averaging

February 25, 2025

The Built-In Robustness of Decentralized Federated Averaging to Bad Data
Load Centrality Federated Averaging Native Robustness State of the Art Robustness Decentralized Manner Influential Node

January 31, 2025

Continuous-Time Analysis of Federated Averaging
Loss Function Federated Averaging Convergence Guarantee Continuous Time Convergence Analysis

January 25, 2025

A Two-Stage CAE-Based Federated Learning Framework for Efficient Jamming Detection in 5G Networks
Data Detection Federated Averaging Multi Stage G Wireless Federated Learning Anti Jamming Jamming Detection G Network Jamming Attack

December 10, 2024

Distributed Gradient Descent with Many Local Steps in Overparameterized Models
Full Model Local SGD Model Convergence Gradient Descent Federated Averaging Local Gradient

December 2, 2024

Refined Analysis of Federated Averaging's Bias and Federated Richardson-Romberg Extrapolation
Cartesian Product Extrapolation Extrapolation Framework Federated Averaging Absolute Stance Bias Markov Process Improved Analysis Federated Prompt Cooperation FedAvg Converges Gradient Noise

November 27, 2024

Task Arithmetic Through The Lens Of One-Shot Federated Learning
Arithmetic Task Multi Task Learning Federated Averaging Camera Lens

November 10, 2024

Client Contribution Normalization for Enhanced Federated Learning
Heterogeneous Data Client Contribution Federated Averaging Centralized Machine Learning

November 2, 2024

Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing
Hyperdimensional Computing Federated Averaging Federated Stochastic

October 4, 2024

BN-SCAFFOLD: controlling the drift of Batch Normalization statistics in Federated Learning
Federated Averaging Batch Normalization New Algorithm Real Drift

October 2, 2024

Debiasing Federated Learning with Correlated Client Participation
Cross Device Federated Learning Federated Averaging Optimal Separation Client Participation

September 11, 2024

Riemannian Federated Learning via Averaging Gradient Stream
Riemannian Geometry Federated Averaging FedAvg Converges Riemannian Stochastic

September 9, 2024

pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning
Diffusion Model Parameter Selection Personalized Federated Learning Federated Averaging

September 8, 2024

DynamicFL: Federated Learning with Dynamic Communication Resource Allocation
Communication Heterogeneity Statistical Heterogeneity Federated Stochastic Federated Averaging

August 27, 2024

Bandwidth-Aware and Overlap-Weighted Compression for Communication-Efficient Federated Learning
Federated Averaging Linear Compression Compression Technique

July 17, 2024

Comparing Federated Stochastic Gradient Descent and Federated Averaging for Predicting Hospital Length of Stay
Federated Averaging Model Training Stochastic Gradient Descent Local Model Federated Stochastic

July 16, 2024

CCVA-FL: Cross-Client Variations Adaptive Federated Learning for Medical Imaging
Synthetic Medical Image Federated Averaging Medical Image Data Medical Imaging

June 18, 2024

Training Diffusion Models with Federated Learning
Diffusion Based Model Diffusion Model Denoising Diffusion Model FedAvg Algorithm Federated Averaging