paper-with-me

홈 › Papers

FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation

2022-12-14 · Ziqing Fan, Yanfeng Wang, Jiangchao Yao, Lingjuan Lyu, Ya zhang, Qi Tian

The statistical heterogeneity of the non-independent and identically distributed (non-IID) data in local clients significantly limits the performance of federated learning. Previous attempts like FedProx, SCAFFOLD, MOON, FedNova and FedDyn resort to an optimization perspective, which requires an auxiliary term or re-weights local updates to calibrate the learning bias or the objective inconsistency. However, in addition to previous explorations for improvement in federated averaging, our analysis shows that another critical bottleneck is the poorer optima of client models in more heterogeneous conditions. We thus introduce a data-driven approach called FedSkip to improve the client optima by periodically skipping federated averaging and scattering local models to the cross devices. We provide theoretical analysis of the possible benefit from FedSkip and conduct extensive experiments on a range of datasets to demonstrate that FedSkip achieves much higher accuracy, better aggregation efficiency and competing communication efficiency. Source code is available at: https://github.com/MediaBrain-SJTU/FedSkip.

📄 PDF Abstract BibTeX arXiv:2212.07224

Code (1)

mediabrain-sjtu/fedskip 공식 구현 pytorch

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

FedSkipTwin: Digital-Twin-Guided Client Skipping for Communication-Efficient Federated Learning

2025-07-18 · Daniel Commey, Kamel Abbad, Garth V. Crosby, Lyes Khoukhi arxiv

Communication overhead remains a primary bottleneck in federated learning (FL), particularly for applications involving mobile and IoT devices with constrained bandwidth. This work introduces FedSkipTwin, a novel client-…

Federated Learning

Federated Learning with Layer Skipping: Efficient Training of Large Language Models for Healthcare NLP

2025-04-13 · Lihong Zhang, Yue Li

Federated learning (FL) enables collaborative model training across organizations without sharing raw data, addressing crucial privacy concerns in healthcare natural language processing (NLP). However, training large lan…

Federated LearningNERPrivacy Preserving

DynamicFL: Federated Learning with Dynamic Communication Resource Allocation

2024-09-08 · Qi Le, Enmao Diao, Xinran Wang, Vahid Tarokh 외

Federated Learning (FL) is a collaborative machine learning framework that allows multiple users to train models utilizing their local data in a distributed manner. However, considerable statistical heterogeneity in loca…

Federated Learning

Towards Robust Federated Analytics via Differentially Private Measurements of Statistical Heterogeneity

2024-11-07 · Mary Scott, Graham Cormode, Carsten Maple

Statistical heterogeneity is a measure of how skewed the samples of a dataset are. It is a common problem in the study of differential privacy that the usage of a statistically heterogeneous dataset results in a signific…

Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms

2022-10-31 · Vincent Plassier, Alain Durmus, Eric Moulines

This paper focuses on Bayesian inference in a federated learning context (FL). While several distributed MCMC algorithms have been proposed, few consider the specific limitations of FL such as communication bottlenecks a…

Bayesian InferenceFederated Learning