paper-with-me

홈 › Papers

FedDD: Toward Communication-efficient Federated Learning with Differential Parameter Dropout

2023-08-31 · Zhiying Feng, Xu Chen, Qiong Wu, Wen Wu, Xiaoxi Zhang, Qianyi Huang

Federated Learning (FL) requires frequent exchange of model parameters, which leads to long communication delay, especially when the network environments of clients vary greatly. Moreover, the parameter server needs to wait for the slowest client (i.e., straggler, which may have the largest model size, lowest computing capability or worst network condition) to upload parameters, which may significantly degrade the communication efficiency. Commonly-used client selection methods such as partial client selection would lead to the waste of computing resources and weaken the generalization of the global model. To tackle this problem, along a different line, in this paper, we advocate the approach of model parameter dropout instead of client selection, and accordingly propose a novel framework of Federated learning scheme with Differential parameter Dropout (FedDD). FedDD consists of two key modules: dropout rate allocation and uploaded parameter selection, which will optimize the model parameter uploading ratios tailored to different clients' heterogeneous conditions and also select the proper set of important model parameters for uploading subject to clients' dropout rate constraints. Specifically, the dropout rate allocation is formulated as a convex optimization problem, taking system heterogeneity, data heterogeneity, and model heterogeneity among clients into consideration. The uploaded parameter selection strategy prioritizes on eliciting important parameters for uploading to speedup convergence. Furthermore, we theoretically analyze the convergence of the proposed FedDD scheme. Extensive performance evaluations demonstrate that the proposed FedDD scheme can achieve outstanding performances in both communication efficiency and model convergence, and also possesses a strong generalization capability to data of rare classes.

📄 PDF Abstract BibTeX arXiv:2308.16835

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Federated Learning for Diffusion Models

2025-03-09 · Zihao Peng, Xijun Wang, Shengbo Chen, HONG RAO 외

Diffusion models are powerful generative models that can produce highly realistic samples for various tasks. Typically, these models are constructed using centralized, independently and identically distributed (IID) trai…

DenoisingFederated Learning

SPD-CFL: Stepwise Parameter Dropout for Efficient Continual Federated Learning

2024-05-15 · Yuning Yang, Han Yu, Chuan Sun, Tianrun Gao 외

Federated Learning (FL) is a collaborative machine learning paradigm for training models on local sensitive data with privacy protection. Pre-trained transformer-based models have emerged as useful foundation models (FMs…

Continual LearningFederated Learningparameter-efficient fine-tuningTransfer Learning

FedSPU: Personalized Federated Learning for Resource-constrained Devices with Stochastic Parameter Update

2024-03-18 · Ziru Niu, Hai Dong, A. K. Qin

Personalized Federated Learning (PFL) is widely employed in IoT applications to handle high-volume, non-iid client data while ensuring data privacy. However, heterogeneous edge devices owned by clients may impose varying…

Federated LearningPersonalized Federated Learning

Fast Server Learning Rate Tuning for Coded Federated Dropout

2022-01-26 · Giacomo Verardo, Daniel Barreira, Marco Chiesa, Dejan Kostic 외

In cross-device Federated Learning (FL), clients with low computational power train a common\linebreak[4] machine model by exchanging parameters via updates instead of potentially private data. Federated Dropout (FD) is …

Federated Learning

Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimation

2024-07-03 · Sajani Vithana, Viveck R. Cadambe, Flavio P. Calmon, Haewon Jeong

Differentially private distributed mean estimation (DP-DME) is a fundamental building block in privacy-preserving federated learning, where a central server estimates the mean of $d$-dimensional vectors held by $n$ users…

Federated LearningPrivacy Preserving