paper-with-me

Papers

Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning

2021-05-12 · Yann Fraboni, Richard Vidal, Laetitia Kameni, Marco Lorenzi

This work addresses the problem of optimizing communications between server and clients in federated learning (FL). Current sampling approaches in FL are either biased, or non optimal in terms of server-clients communications and training stability. To overcome this issue, we introduce \textit{clustered sampling} for clients selection. We prove that clustered sampling leads to better clients representatitivity and to reduced variance of the clients stochastic aggregation weights in FL. Compatibly with our theory, we provide two different clustering approaches enabling clients aggregation based on 1) sample size, and 2) models similarity. Through a series of experiments in non-iid and unbalanced scenarios, we demonstrate that model aggregation through clustered sampling consistently leads to better training convergence and variability when compared to standard sampling approaches. Our approach does not require any additional operation on the clients side, and can be seamlessly integrated in standard FL implementations. Finally, clustered sampling is compatible with existing methods and technologies for privacy enhancement, and for communication reduction through model compression.

📄 PDF Abstract BibTeX arXiv:2105.05883

Code (1)

Accenture/Labs-Federated-Learning 공식 구현 pytorch

Tasks

ClusteringFederated LearningModel Compression

Similar Papers 제목 키워드 기반

Design-Based Multi-Way Clustering

2023-09-04 · Luther Yap

This paper extends the design-based framework to settings with multi-way cluster dependence, and shows how multi-way clustering can be justified when clustered assignment and clustered sampling occurs on different dimens…

Clusteringvalid

Prediction of microstructural representativity from a single image

2024-10-25 · Amir Dahari, Ronan Docherty, Steve Kench, Samuel J. Cooper

In this study, we present a method for predicting the representativity of the phase fraction observed in a single image (2D or 3D) of a material. Traditional approaches often require large datasets and extensive statisti…

Prediction

Find Your Optimal Assignments On-the-fly: A Holistic Framework for Clustered Federated Learning

2023-10-09 · Yongxin Guo, Xiaoying Tang, Tao Lin

Federated Learning (FL) is an emerging distributed machine learning approach that preserves client privacy by storing data on edge devices. However, data heterogeneity among clients presents challenges in training models…

ClusteringFederated Learning

Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matching

2022-03-23 · Zexi Li, Jiaxun Lu, Shuang Luo, Didi Zhu 외

In federated learning (FL), clients may have diverse objectives, and merging all clients' knowledge into one global model will cause negative transfer to local performance. Thus, clustered FL is proposed to group similar…

Federated Learning

Interaction-Aware Gaussian Weighting for Clustered Federated Learning

2025-02-05 · Alessandro Licciardi, Davide Leo, Eros Faní, Barbara Caputo 외

Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clust…

ClusteringFederated Learning