Show simple item record

AuthorRiahi, Ali
AuthorMohamed, Amr
AuthorErbad, Aiman
Available date2023-05-21T09:00:58Z
Publication Date2023-02-01
Publication NameIEEE Transactions on Network and Service Management
Identifierhttp://dx.doi.org/10.1109/TNSM.2023.3241437
CitationRiahi, A., Mohamed, A., & Erbad, A. (2023). RL-Based Federated Learning Framework Over Blockchain (RL-FL-BC). IEEE Transactions on Network and Service Management.
ISSN1932-4537
URIhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85148445060&origin=inward
URIhttp://hdl.handle.net/10576/43120
AbstractFederated learning (FL) paradigms aim to amalgamate diverse data properties stored locally at each user, while preserving data privacy through sharing users’ learning experiences and iteratively aggregating their local learning models into a global one. However, the majority of FL architectures with centralized cloud do not guarantee the trust in sharing users’ models, and hence, open the door for slowing and/or contaminating the global learning experience. In this paper, we propose a decentralized Blockchain (BC)-based framework and define a comprehensive protocol for exchanging local models, in order to guarantee users’ mutual trust while sharing their local learning experiences. We then propose a technique to optimize the global learning experience using Reinforcement Learning (RL), namely RL-FL-BC, to tackle the trade-off between information age of the learning parameters, data skewness (i.e., non-iid), and BC transaction cost (i.e., Ether price). We implement the proposed framework in a realistic containerized environment to facilitate the comparative study of the RL-FL-BC technique with baselines techniques. Our results show the efficacy of the BC-based protocol to facilitate the exchange of both the models’ and the optimization parameters to guarantee users’ mutual trust, while improving global learning performance compared to baselines techniques.
Languageen
PublisherIEEE
SubjectBiological system modeling
Blockchain (BC)
Blockchains
Data models
Data privacy
Deep Q Network (DQN)
Federated learning
Federated Learning (FL)
Internet of Things
Internet of Things (IoT)
Machine Learning (ML)
Medical services
Reinforcement Learning (RL)
TitleRL-Based Federated Learning Framework Over Blockchain (RL-FL-BC)
TypeArticle
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record