paper-with-me

홈 › Papers

Client-Edge-Cloud Hierarchical Federated Learning

2019-05-16 · Lumin Liu, Jun Zhang, S. H. Song, Khaled B. Letaief

Federated Learning is a collaborative machine learning framework to train a deep learning model without accessing clients' private data. Previous works assume one central parameter server either at the cloud or at the edge. The cloud server can access more data but with excessive communication overhead and long latency, while the edge server enjoys more efficient communications with the clients. To combine their advantages, we propose a client-edge-cloud hierarchical Federated Learning system, supported with a HierFAVG algorithm that allows multiple edge servers to perform partial model aggregation. In this way, the model can be trained faster and better communication-computation trade-offs can be achieved. Convergence analysis is provided for HierFAVG and the effects of key parameters are also investigated, which lead to qualitative design guidelines. Empirical experiments verify the analysis and demonstrate the benefits of this hierarchical architecture in different data distribution scenarios. Particularly, it is shown that by introducing the intermediate edge servers, the model training time and the energy consumption of the end devices can be simultaneously reduced compared to cloud-based Federated Learning.

📄 PDF Abstract BibTeX arXiv:1905.06641

Code (1)

LuminLiu/HierFL pytorch

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Hierarchical Federated Learning with Quantization: Convergence Analysis and System Design

2021-03-26 · Lumin Liu, Jun Zhang, Shenghui Song, Khaled B. Letaief

Federated learning (FL) is a powerful distributed machine learning framework where a server aggregates models trained by different clients without accessing their private data. Hierarchical FL, with a client-edge-cloud a…

Federated LearningQuantization

Timely Asynchronous Hierarchical Federated Learning: Age of Convergence

2023-06-21 · Purbesh Mitra, Sennur Ulukus

We consider an asynchronous hierarchical federated learning (AHFL) setting with a client-edge-cloud framework. The clients exchange the trained parameters with their corresponding edge servers, which update the locally a…

Federated Learning

HiFlash: Communication-Efficient Hierarchical Federated Learning with Adaptive Staleness Control and Heterogeneity-aware Client-Edge Association

2023-01-16 · Qiong Wu, Xu Chen, Tao Ouyang, Zhi Zhou 외

Federated learning (FL) is a promising paradigm that enables collaboratively learning a shared model across massive clients while keeping the training data locally. However, for many existing FL systems, clients need to …

Deep Reinforcement LearningEdge-computingFederated Learning

SHFL: Secure Hierarchical Federated Learning Framework for Edge Networks

2024-09-23 · Omid Tavallaie, Kanchana Thilakarathna, Suranga Seneviratne, Aruna Seneviratne 외

Federated Learning (FL) is a distributed machine learning paradigm designed for privacy-sensitive applications that run on resource-constrained devices with non-Identically and Independently Distributed (IID) data. Tradi…

Data PoisoningEdge-computingFederated Learning

HierSFL: Local Differential Privacy-aided Split Federated Learning in Mobile Edge Computing

2024-01-16 · Minh K. Quan, Dinh C. Nguyen, Van-Dinh Nguyen, Mayuri Wijayasundara 외

Federated Learning is a promising approach for learning from user data while preserving data privacy. However, the high requirements of the model training process make it difficult for clients with limited memory or band…

Edge-computingFederated Learning