paper-with-me

Papers

Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing

2024-05-25 · Yongxin Guo, Lin Wang, Xiaoying Tang, Tao Lin

Federated Learning (FL) is a privacy-preserving distributed machine learning paradigm. Nonetheless, the substantial distribution shifts among clients pose a considerable challenge to the performance of current FL algorithms. To mitigate this challenge, various methods have been proposed to enhance the FL training process. This paper endeavors to tackle the issue of data heterogeneity from another perspective -- by improving FL algorithms prior to the actual training stage. Specifically, we introduce the Client2Vec mechanism, which generates a unique client index for each client before the commencement of FL training. Subsequently, we leverage the generated client index to enhance the subsequent FL training process. To demonstrate the effectiveness of the proposed Client2Vec method, we conduct three case studies that assess the impact of the client index on the FL training process. These case studies encompass enhanced client sampling, model aggregation, and local training. Extensive experiments conducted on diverse datasets and model architectures show the efficacy of Client2Vec across all three case studies. Our code is avaliable at \url{https://github.com/LINs-lab/client2vec}.

📄 PDF Abstract BibTeX arXiv:2405.16233

Code (1)

lins-lab/client2vec 공식 구현

Tasks

Federated LearningPrivacy Preserving

Similar Papers 제목 키워드 기반

pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data

2025-11-22 · Md Akil Raihan Iftee, Syed Md. Ahnaf Hasan, Mir Sazzat Hossain, Rakibul Hasan Rajib 외 arxiv

Test-time adaptation (TTA) in federated learning (FL) is crucial for handling unseen data distributions across clients, particularly when faced with domain shifts and skewed class distributions. Class Imbalance (CI) rema…

Test-time AdaptationFederated Learning

Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning

2024-12-26 · Xingbo Fu, Zihan Chen, Yinhan He, Song Wang 외

Federated Graph Learning (FGL) enables multiple clients to jointly train powerful graph learning models, e.g., Graph Neural Networks (GNNs), without sharing their local graph data for graph-related downstream tasks, such…

Graph LearningGraph Property PredictionProperty Prediction

Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift

2026-03-01 · Heewon Park, Mugon Joe, Miru Kim, Kyungjin Im 외 arxiv

Federated learning (FL) in post-deployment settings must adapt to non-stationary data streams across heterogeneous clients without access to ground-truth labels. A major challenge is learning rate selection under client-…

Federated Learning

Detecting Atypical Clients in Federated Learning via Representation-Level Divergence

2026-05-21 · Cristian Pérez-Corral, Jose I. Mestre, Alberto Fernández-Hernández, Manuel F. Dolz 외 arxiv

Federated learning enables collaborative training across distributed clients with heterogeneous data, but such heterogeneity often leads to unstable updates and degraded global performance. Moreover, in practical deploym…

Federated Learning

FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts

2025-11-27 · Dario Fenoglio, Mohan Li, Pietro Barbiero, Nicholas D. Lane 외 arxiv

Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy. Traditional FL methods often use a global model to fit all clients, assuming that clients' data are inde…

Test-time AdaptationFederated Learning