The GA presents the research objectives, methodologies, and findings of our work, which involves the implementation of Federated Learning without a central server using s...
Abstract:
Federated Learning (FL) presents a mechanism to allow decentralized training for machine learning (ML) models inherently enabling privacy preservation. The classical FL i...Show MoreMetadata
Abstract:
Federated Learning (FL) presents a mechanism to allow decentralized training for machine learning (ML) models inherently enabling privacy preservation. The classical FL is implemented as a client-server system, which is known as Centralised Federated Learning (CFL). There are challenges inherent in CFL since all participants need to interact with a central server resulting in a potential communication bottleneck and a single point of failure. In addition, it is difficult to have a central server in some scenarios due to the implementation cost and complexity. This study aims to use Decentralized Federated learning (DFL) without a central server through one-hop neighbours. Such collaboration depends on the dynamics of communication networks, e.g., the topology of the network, the MAC protocol, and both large-scale and small-scale fading on links. In this paper, we employ stochastic geometry to model these dynamics explicitly, allowing us to quantify the performance of the DFL. The core objective is to achieve better classification without sacrificing privacy while accommodating for networking dynamics. In this paper, we are interested in how such topologies impact the performance of ML when deployed in practice. The proposed system is trained on a well-known MINST dataset for benchmarking, which contains labelled data samples of 60K images each with a size 28\times 28 pixels, and 1000 random samples of this MNIST dataset are assigned for each participant’ device. The participants’ devices implement a CNN model as a classifier model. To evaluate the performance of the model, a number of participants are randomly selected from the network. Due to randomness in the communication process, these participants interact with the random number of nodes in the neighbourhood to exchange model parameters which are subsequently used to update the participants’ individual models. These participants connected successfully with a varying number of neighbours to exchange paramete...
The GA presents the research objectives, methodologies, and findings of our work, which involves the implementation of Federated Learning without a central server using s...
Published in: IEEE Access ( Volume: 11)
Funding Agency:

Department of Electrical and Electronic Engineering, University of Leeds, Leeds, U.K.
Abdelaziz Salama (Member, IEEE) received the B.Sc. degree in electrical and electronic engineering from Tripoli University, Tripoli, Libya, in 2009, and the M.Sc. degree in communication, control and digital signal processing from the University of Strathclyde, Glasgow, U.K., in 2017. He is currently pursuing the Ph.D. degree with the University of Leeds, Leeds, U.K. He worked for nine years at local and international fir...Show More
Abdelaziz Salama (Member, IEEE) received the B.Sc. degree in electrical and electronic engineering from Tripoli University, Tripoli, Libya, in 2009, and the M.Sc. degree in communication, control and digital signal processing from the University of Strathclyde, Glasgow, U.K., in 2017. He is currently pursuing the Ph.D. degree with the University of Leeds, Leeds, U.K. He worked for nine years at local and international fir...View more

Department of Electrical and Electronic Engineering, University of Leeds, Leeds, U.K.
Achilleas Stergioulis (Member, IEEE) received the M.Eng. degree in electrical and computer engineering from the Aristotle University of Thessaloniki, Greece, in 2020, and the M.Sc. degree in embedded systems engineering from the School of Electrical and Electronic Engineering, University of Leeds, in 2021, where he focused on applying decentralized federated learning in aid of communication systems. As part of his undergr...Show More
Achilleas Stergioulis (Member, IEEE) received the M.Eng. degree in electrical and computer engineering from the Aristotle University of Thessaloniki, Greece, in 2020, and the M.Sc. degree in embedded systems engineering from the School of Electrical and Electronic Engineering, University of Leeds, in 2021, where he focused on applying decentralized federated learning in aid of communication systems. As part of his undergr...View more

Department of Electrical Engineering, Faculty of Engineering, The Hashemite University, Zarqa, Jordan
Ali M. Hayajneh (Member, IEEE) received the B.Sc. and M.Sc. degrees from the Jordan University of Science and Technology (JUST), Irbid, Jordan, in 2010 and 2014, respectively, and the Ph.D. degree from the University of Leeds, Leeds, U.K. He is currently with the Department of Electrical Engineering, Faculty of Engineering, The Hashemite University, Zarqa, Jordan. He is also the Director of the Innovation and Entrepreneur...Show More
Ali M. Hayajneh (Member, IEEE) received the B.Sc. and M.Sc. degrees from the Jordan University of Science and Technology (JUST), Irbid, Jordan, in 2010 and 2014, respectively, and the Ph.D. degree from the University of Leeds, Leeds, U.K. He is currently with the Department of Electrical Engineering, Faculty of Engineering, The Hashemite University, Zarqa, Jordan. He is also the Director of the Innovation and Entrepreneur...View more

Department of Electrical and Electronic Engineering, University of Leeds, Leeds, U.K.
Syed Ali Raza Zaidi (Senior Member, IEEE) received the Ph.D. degree from the School of Electronic and Electrical Engineering. From 2011 to 2013, he was associated with the International University of Rabat working as a Research Associate. He was also a Visiting Research Scientist at Qatar Innovations and Mobility Centre, from October 2013 to December 2013, working on QNRF funded project QSON. From 2013 to 2015, he was ass...Show More
Syed Ali Raza Zaidi (Senior Member, IEEE) received the Ph.D. degree from the School of Electronic and Electrical Engineering. From 2011 to 2013, he was associated with the International University of Rabat working as a Research Associate. He was also a Visiting Research Scientist at Qatar Innovations and Mobility Centre, from October 2013 to December 2013, working on QNRF funded project QSON. From 2013 to 2015, he was ass...View more

Department of Electrical and Electronic Engineering, University of Leeds, Leeds, U.K.
Des Mclernon (Member, IEEE) received the B.Sc. degree in electronic and electrical engineering and the M.Sc. degree in electronics from the Queen’s University of Belfast, Ireland, and the Ph.D. degree in signal processing from the Imperial College, University of London, U.K. He was working on radar systems research with Ferranti Ltd., Edinburgh, Scotland. He is currently a Reader of signal processing with the University o...Show More
Des Mclernon (Member, IEEE) received the B.Sc. degree in electronic and electrical engineering and the M.Sc. degree in electronics from the Queen’s University of Belfast, Ireland, and the Ph.D. degree in signal processing from the Imperial College, University of London, U.K. He was working on radar systems research with Ferranti Ltd., Edinburgh, Scotland. He is currently a Reader of signal processing with the University o...View more

Department of Electrical and Electronic Engineering, University of Leeds, Leeds, U.K.
Ian Robertson (Fellow, IEEE) is a Professor of RF and microwave engineering. He has published over 400 peer-reviewed research papers. He edited the book titled MMIC Design (IEEE, 1995) and co-edited the book titled RFIC & MMIC Design and Technology (published in English in 2001, and in Chinese in 2007). In 2016, he coauthored the book titled Microwave and Millimetre-Wave Design for Wireless Communications (Wiley). The fun...Show More
Ian Robertson (Fellow, IEEE) is a Professor of RF and microwave engineering. He has published over 400 peer-reviewed research papers. He edited the book titled MMIC Design (IEEE, 1995) and co-edited the book titled RFIC & MMIC Design and Technology (published in English in 2001, and in Chinese in 2007). In 2016, he coauthored the book titled Microwave and Millimetre-Wave Design for Wireless Communications (Wiley). The fun...View more

Department of Electrical and Electronic Engineering, University of Leeds, Leeds, U.K.
Abdelaziz Salama (Member, IEEE) received the B.Sc. degree in electrical and electronic engineering from Tripoli University, Tripoli, Libya, in 2009, and the M.Sc. degree in communication, control and digital signal processing from the University of Strathclyde, Glasgow, U.K., in 2017. He is currently pursuing the Ph.D. degree with the University of Leeds, Leeds, U.K. He worked for nine years at local and international firms, in several positions, in the areas of telecommunication engineering, and information technology and management. His research interests include federated learning, and autonomous systems and sensing.
Abdelaziz Salama (Member, IEEE) received the B.Sc. degree in electrical and electronic engineering from Tripoli University, Tripoli, Libya, in 2009, and the M.Sc. degree in communication, control and digital signal processing from the University of Strathclyde, Glasgow, U.K., in 2017. He is currently pursuing the Ph.D. degree with the University of Leeds, Leeds, U.K. He worked for nine years at local and international firms, in several positions, in the areas of telecommunication engineering, and information technology and management. His research interests include federated learning, and autonomous systems and sensing.View more

Department of Electrical and Electronic Engineering, University of Leeds, Leeds, U.K.
Achilleas Stergioulis (Member, IEEE) received the M.Eng. degree in electrical and computer engineering from the Aristotle University of Thessaloniki, Greece, in 2020, and the M.Sc. degree in embedded systems engineering from the School of Electrical and Electronic Engineering, University of Leeds, in 2021, where he focused on applying decentralized federated learning in aid of communication systems. As part of his undergraduate diploma dissertation, he carried out research on causal analysis and inference in the presence of missing data. He is currently working as a digital design engineer in the semiconductor industry.
Achilleas Stergioulis (Member, IEEE) received the M.Eng. degree in electrical and computer engineering from the Aristotle University of Thessaloniki, Greece, in 2020, and the M.Sc. degree in embedded systems engineering from the School of Electrical and Electronic Engineering, University of Leeds, in 2021, where he focused on applying decentralized federated learning in aid of communication systems. As part of his undergraduate diploma dissertation, he carried out research on causal analysis and inference in the presence of missing data. He is currently working as a digital design engineer in the semiconductor industry.View more

Department of Electrical Engineering, Faculty of Engineering, The Hashemite University, Zarqa, Jordan
Ali M. Hayajneh (Member, IEEE) received the B.Sc. and M.Sc. degrees from the Jordan University of Science and Technology (JUST), Irbid, Jordan, in 2010 and 2014, respectively, and the Ph.D. degree from the University of Leeds, Leeds, U.K. He is currently with the Department of Electrical Engineering, Faculty of Engineering, The Hashemite University, Zarqa, Jordan. He is also the Director of the Innovation and Entrepreneurial Projects Center, The Hashemite University. His current research is funded by the Royal Academy of Engineering through two programs: 1) “Transfer Systems Through Partnerships (TSP)” and 2) “Distinguished International Associate (DIA)” in the fields of smart agriculture, drone-assisted micro irrigation, and tiny machine learning on edge IoT devices. His current research interests include drone-assisted wireless communications, public safety communication networks, backscatter communication, deep learning, power harvesting, stochastic geometry, device-to-device (D2D) and machine-to-machine (M2M) communications, modeling of heterogeneous networks, cognitive radio networks, cooperative relay networks, edge computing, and reinforcement learning.
Ali M. Hayajneh (Member, IEEE) received the B.Sc. and M.Sc. degrees from the Jordan University of Science and Technology (JUST), Irbid, Jordan, in 2010 and 2014, respectively, and the Ph.D. degree from the University of Leeds, Leeds, U.K. He is currently with the Department of Electrical Engineering, Faculty of Engineering, The Hashemite University, Zarqa, Jordan. He is also the Director of the Innovation and Entrepreneurial Projects Center, The Hashemite University. His current research is funded by the Royal Academy of Engineering through two programs: 1) “Transfer Systems Through Partnerships (TSP)” and 2) “Distinguished International Associate (DIA)” in the fields of smart agriculture, drone-assisted micro irrigation, and tiny machine learning on edge IoT devices. His current research interests include drone-assisted wireless communications, public safety communication networks, backscatter communication, deep learning, power harvesting, stochastic geometry, device-to-device (D2D) and machine-to-machine (M2M) communications, modeling of heterogeneous networks, cognitive radio networks, cooperative relay networks, edge computing, and reinforcement learning.View more

Department of Electrical and Electronic Engineering, University of Leeds, Leeds, U.K.
Syed Ali Raza Zaidi (Senior Member, IEEE) received the Ph.D. degree from the School of Electronic and Electrical Engineering. From 2011 to 2013, he was associated with the International University of Rabat working as a Research Associate. He was also a Visiting Research Scientist at Qatar Innovations and Mobility Centre, from October 2013 to December 2013, working on QNRF funded project QSON. From 2013 to 2015, he was associated with the SPCOM Research Group working on U.S. ARL-funded project in the area of network science. He is currently an Associate Professor with the University of Leeds in the broad area of communication and sensing for robotics and autonomous systems. He has published more than 90 papers in leading IEEE conferences and journals. He has been awarded COST IC0902, Royal Academy of Engineering, EPSRC, Horizon EU, and DAAD grants to promote his research outputs. His current research interests include ICT, applied mathematics, mobile computing, and embedded systems implementation. Specifically, his current research is geared toward: 1) design and implementation of communication protocols to enable various applications (rehabilitation, healthcare, manufacturing, and surveillance) of future RAS and 2) design, implementation, and control of RAS for enabling future wireless networks (e.g., autonomous deployment and management and repair of future cellular networks). He was awarded the G. W. and F. W. Carter Prize for best thesis and best research paper. From 2014 to 2015, he was an Editor of the IEEE Communication Letters and a Lead Guest Editor of IET Signal Processing Special Issue on Signal Processing for Large Scale 5G Wireless Networks. He is also an Editor of IET Access, Fronthaul, and Backhaul books. He is also serving as an Associate Technical Editor for IEEE Communications Magazine.
Syed Ali Raza Zaidi (Senior Member, IEEE) received the Ph.D. degree from the School of Electronic and Electrical Engineering. From 2011 to 2013, he was associated with the International University of Rabat working as a Research Associate. He was also a Visiting Research Scientist at Qatar Innovations and Mobility Centre, from October 2013 to December 2013, working on QNRF funded project QSON. From 2013 to 2015, he was associated with the SPCOM Research Group working on U.S. ARL-funded project in the area of network science. He is currently an Associate Professor with the University of Leeds in the broad area of communication and sensing for robotics and autonomous systems. He has published more than 90 papers in leading IEEE conferences and journals. He has been awarded COST IC0902, Royal Academy of Engineering, EPSRC, Horizon EU, and DAAD grants to promote his research outputs. His current research interests include ICT, applied mathematics, mobile computing, and embedded systems implementation. Specifically, his current research is geared toward: 1) design and implementation of communication protocols to enable various applications (rehabilitation, healthcare, manufacturing, and surveillance) of future RAS and 2) design, implementation, and control of RAS for enabling future wireless networks (e.g., autonomous deployment and management and repair of future cellular networks). He was awarded the G. W. and F. W. Carter Prize for best thesis and best research paper. From 2014 to 2015, he was an Editor of the IEEE Communication Letters and a Lead Guest Editor of IET Signal Processing Special Issue on Signal Processing for Large Scale 5G Wireless Networks. He is also an Editor of IET Access, Fronthaul, and Backhaul books. He is also serving as an Associate Technical Editor for IEEE Communications Magazine.View more

Department of Electrical and Electronic Engineering, University of Leeds, Leeds, U.K.
Des Mclernon (Member, IEEE) received the B.Sc. degree in electronic and electrical engineering and the M.Sc. degree in electronics from the Queen’s University of Belfast, Ireland, and the Ph.D. degree in signal processing from the Imperial College, University of London, U.K. He was working on radar systems research with Ferranti Ltd., Edinburgh, Scotland. He is currently a Reader of signal processing with the University of Leeds, U.K. His research interests include signal processing for wireless communications. In these fields, he has around 350 research publications and has also supervised over 50 Ph.D. students.
Des Mclernon (Member, IEEE) received the B.Sc. degree in electronic and electrical engineering and the M.Sc. degree in electronics from the Queen’s University of Belfast, Ireland, and the Ph.D. degree in signal processing from the Imperial College, University of London, U.K. He was working on radar systems research with Ferranti Ltd., Edinburgh, Scotland. He is currently a Reader of signal processing with the University of Leeds, U.K. His research interests include signal processing for wireless communications. In these fields, he has around 350 research publications and has also supervised over 50 Ph.D. students.View more

Department of Electrical and Electronic Engineering, University of Leeds, Leeds, U.K.
Ian Robertson (Fellow, IEEE) is a Professor of RF and microwave engineering. He has published over 400 peer-reviewed research papers. He edited the book titled MMIC Design (IEEE, 1995) and co-edited the book titled RFIC & MMIC Design and Technology (published in English in 2001, and in Chinese in 2007). In 2016, he coauthored the book titled Microwave and Millimetre-Wave Design for Wireless Communications (Wiley). The funded projects that he has recently been involved in include “Pervasive Sensing for Buried Pipes,” led by The University of Sheffield, which involves studying advanced robotic swarms that can inspect and repair the underground pipe network. His current research interests include microwave and millimeter-wave design for applications in the Internet of Things (IoT), robotics, wearable electronics, biosensors, wireless power transfer, and 5G/6G communications systems. He was elected as a fellow of the IEEE, in 2012, in recognition of his contributions to MMIC design techniques and millimeter-wave system-in-package technology. He was the General Technical Program Committee Chair of the European Microwave Week, in 2011 and 2016.
Ian Robertson (Fellow, IEEE) is a Professor of RF and microwave engineering. He has published over 400 peer-reviewed research papers. He edited the book titled MMIC Design (IEEE, 1995) and co-edited the book titled RFIC & MMIC Design and Technology (published in English in 2001, and in Chinese in 2007). In 2016, he coauthored the book titled Microwave and Millimetre-Wave Design for Wireless Communications (Wiley). The funded projects that he has recently been involved in include “Pervasive Sensing for Buried Pipes,” led by The University of Sheffield, which involves studying advanced robotic swarms that can inspect and repair the underground pipe network. His current research interests include microwave and millimeter-wave design for applications in the Internet of Things (IoT), robotics, wearable electronics, biosensors, wireless power transfer, and 5G/6G communications systems. He was elected as a fellow of the IEEE, in 2012, in recognition of his contributions to MMIC design techniques and millimeter-wave system-in-package technology. He was the General Technical Program Committee Chair of the European Microwave Week, in 2011 and 2016.View more