A Comprehensive Survey on Federated Learning: Concept and Applications

Mahlool, Dhurgham Hassan; Abed, Mohammed Hamzah

doi:10.1007/978-981-19-2069-1_37

Cited by 22 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Federated Learning [1], [15], [16], [17], [26] is a decentralized machine learning technique that trains neural network models using data sources "owned" by multiple clients (Figure 1a). A logically centralized parameter server holds the latest neural network model, and orchestrates the sharing of its weights between all clients.…”

Section: Distributed Learning Architectures: Background and Related Workmentioning

confidence: 99%

“…CENTRALIZED machine learning (ML) training is becoming unsustainable [1]. Aside from the advantages of re-training often to optimize revenues [2], several learning applications need to run their processes at the edge of the network, not in the core of a datacenter, for multiple reasons, including end-to-end latency minimization by running machine learning algorithms locally on an end-device, and privacy concerns of trusting third-party clouds [3].…”

Section: Introductionmentioning

confidence: 99%

“…Different distributed neural network architectures have been proposed to preserve privacy and guarantee timely convergence -for example Federated Learning [1], Split Learning [10], or hybrid approaches [11], [12], [13]. Federated Learning (FL) [14] averages the weights of the learned Neural Network model on each edge device to create a single model, which will update the local ones.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Privacy and Efficiency of Communications in Federated Split Learning

Zhang¹,

Pinto²,

Turina³

et al. 2023

Preprint

View full text Add to dashboard Cite

Everyday, large amounts of sensitive data is distributed across mobile phones, wearable devices, and other sensors. Traditionally, these enormous datasets have been processed on a single system, with complex models being trained to make valuable predictions. Distributed machine learning techniques such as Federated and Split Learning have recently been developed to protect user data and privacy better while ensuring high performance. Both of these distributed learning architectures have advantages and disadvantages. In this paper, we examine these tradeoffs and suggest a new hybrid Federated Split Learning architecture that combines the efficiency and privacy benefits of both. Our evaluation demonstrates how our hybrid Federated Split Learning approach can lower the amount of processing power required by each client running a distributed learning system, reduce training and inference time while keeping a similar accuracy. We also discuss the resiliency of our approach to deep learning privacy inference attacks and compare our solution to other recently proposed benchmarks.

show abstract

Section: Distributed Learning Architectures: Background and Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Privacy and Efficiency of Communications in Federated Split Learning

Zhang¹,

Pinto²,

Turina³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Os VANTs que atuam como infraestrutura de redes móveis podem conter dados que necessitam de seguranc ¸a e privacidade, como por exemplo, a localizac ¸ão, identidade e consumo de energia, bem como, o conjunto de características da distribuic ¸ão espacial e temporal do deslocamento dos usuários terrestres [Brik et al 2020]. Além do mais, as abordagens tradicionais de Aprendizado Profundo (Deep Learning -DL) são centradas na nuvem, gerando uma sobrecarga de comunicac ¸ão da rede e resultando em atrasos de propagac ¸ão [Mahlool and Abed 2022]. Isto pode comprometer a eficiência energética dos dispositivos e sobrecarregar as redes de acesso e o núcleo das redes móveis, inviabilizando determinadas aplicac ¸ões em tempo real.…”

Section: Introduc ¸ãOunclassified

Aprendizado Federado e Deep Q-Network habilitando VANTs como Infraestrutura em Redes 6G

Oliveira¹,

Silva²,

Freitas³

et al. 2023

Anais Do III Workshop De Redes 6G (W6G 2023)

View full text Add to dashboard Cite

A implantação de Veículos Aéreos Não Tripulados (VANTs) como estações base aéreas é um habilitador chave para diferentes casos de uso emergentes das redes 6G. Neste contexto, este artigo apresenta uma proposição para o posicionamento de VANTs atuando como infraestrutura de redes móveis assistidas por Federated Deep Learning (FDL) e Deep Q-Network (DQN). A proposta é baseada em um paradigma de aprendizado descentralizado que melhora a sobrecarga de comunicação com foco na preservação da privacidade e adaptação dinâmica dos VANTs ao ambiente de propagação das redes móveis.

show abstract

“…In this paper, the major problem is how we can implement an intelligent model able to detect BTs in a distributed environment. All the clinics and hospitals have their data, and these data are non-shareable because of the privacy issuers regarding the patients; therefore, the concept of federated learning (FL) and distributed system comes into the picture, where the training implemented locally at each client or hospital then only the training parameters are sharing between them without any share of patient's information [13]. The main contributions of this work are designing the CNN model for each client and exchanging the training parameters between clients and server.…”

mentioning

confidence: 99%

Distributed brain tumor diagnosis using a federated learning environment

Mahlool

Abed

2022

Bulletin EEI

Self Cite

View full text Add to dashboard Cite

In the last few years, a very huge development has occurred in medical techniques using artificial intelligence tools, especially in the diagnosis field. One of the essential things is brain tumor (BT) detection and diagnosis. This kind of disease needs an expert physician to decide on the treatment or surgical operation based on magnetic resonance imaging (MRI) images; therefore, the researchers focus on such kind of medical images analysis and understanding to help the specialist to make a decision. in this work, a new environment has been investigated based on the deep learning method and distributed federated learning (FL) algorithm. The proposed model has been evaluated based on cross-validation techniques using two different standard datasets, BT-small-2c, and BT-large-3c. The achieved classification accuracy was 0.82 and 0.96 consecutively. The proposed classification model provides an active and effective system for assessing BT classification with high reliability and accurate clinical findings.

show abstract

A Comprehensive Survey on Federated Learning: Concept and Applications

Cited by 22 publications

References 36 publications

Privacy and Efficiency of Communications in Federated Split Learning

Privacy and Efficiency of Communications in Federated Split Learning

Aprendizado Federado e Deep Q-Network habilitando VANTs como Infraestrutura em Redes 6G

Distributed brain tumor diagnosis using a federated learning environment

Contact Info

Product

Resources

About