Loading [MathJax]/extensions/MathZoom.js
A Survey on Federated Learning for Resource-Constrained IoT Devices | IEEE Journals & Magazine | IEEE Xplore
Subscribe
ADVANCED SEARCH
Journals & Magazines >IEEE Internet of Things Journal >Volume: 9 Issue: 1

A Survey on Federated Learning for Resource-Constrained IoT Devices

PDF
Ahmed Imteaj; Urmish Thakker; Shiqiang Wang; Jian Li; M. Hadi Amini
All Authors

Abstract:

Federated learning (FL) is a distributed machine learning strategy that generates a global model by learning from multiple decentralized edge clients. FL enables on-devic...Show More

Metadata

Abstract:

Federated learning (FL) is a distributed machine learning strategy that generates a global model by learning from multiple decentralized edge clients. FL enables on-device training, keeping the client’s local data private, and further, updating the global model based on the local model updates. While FL methods offer several advantages, including scalability and data privacy, they assume there are available computational resources at each edge-device/client. However, the Internet-of-Things (IoT)-enabled devices, e.g., robots, drone swarms, and low-cost computing devices (e.g., Raspberry Pi), may have limited processing ability, low bandwidth and power, or limited storage capacity. In this survey article, we propose to answer this question: how to train distributed machine learning models for resource-constrained IoT devices? To this end, we first explore the existing studies on FL, relative assumptions for distributed implementation using IoT devices, and explore their drawbacks. We then discuss the implementation challenges and issues when applying FL to an IoT environment. We highlight an overview of FL and provide a comprehensive survey of the problem statements and emerging challenges, particularly during applying FL within heterogeneous IoT environments. Finally, we point out the future research directions for scientists and researchers who are interested in working at the intersection of FL and resource-constrained IoT environments.
Published in: IEEE Internet of Things Journal ( Volume: 9, Issue: 1, 01 January 2022)
Page(s): 1 - 24
Date of Publication: 06 July 2021

ISSN Information:

DOI: 10.1109/JIOT.2021.3095077
Author image of Ahmed Imteaj
Knight Foundation School of Computing and Information Sciences and the Sustainability, Optimization, and Learning for Interdependent Networks Laboratory, Florida International University, Miami, FL, USA
Ahmed Imteaj received the B.Sc. degree in computer science and engineering from Chittagong University of Engineering and Technology, Chittagong, Bangladesh, in 2015. He is currently pursuing the Ph.D. degree with Florida International University, Miami, FL, USA.
He is a Graduate Assistant with the Knight Foundation School of Computing and Information Sciences, Florida International University, where he is also a Research L...Show More
Ahmed Imteaj received the B.Sc. degree in computer science and engineering from Chittagong University of Engineering and Technology, Chittagong, Bangladesh, in 2015. He is currently pursuing the Ph.D. degree with Florida International University, Miami, FL, USA.
He is a Graduate Assistant with the Knight Foundation School of Computing and Information Sciences, Florida International University, where he is also a Research L...View more
Author image of Urmish Thakker
Deep Learning Research, SambaNova Systems, Palo Alto, CA, USA
Urmish Thakker received the bachelor’s degree from Birla Institute of Technology and Science Pilani, Pilani, India, in 2012, and the master’s degree in computer science from UW Madison, Madison, WI, USA.
He is a Deep Learning Researcher with SambaNova Systems, Palo Alto, CA, USA. Before joining SambaNova, he worked with Arm Research, Texas Instruments and Broadcom, AMD, Santa Clara, CA, USA. Specifically, he has worked on ...Show More
Urmish Thakker received the bachelor’s degree from Birla Institute of Technology and Science Pilani, Pilani, India, in 2012, and the master’s degree in computer science from UW Madison, Madison, WI, USA.
He is a Deep Learning Researcher with SambaNova Systems, Palo Alto, CA, USA. Before joining SambaNova, he worked with Arm Research, Texas Instruments and Broadcom, AMD, Santa Clara, CA, USA. Specifically, he has worked on ...View more
Author image of Shiqiang Wang
IBM T. J. Watson Research Center, Yorktown Heights, NY, USA
Shiqiang Wang (Member, IEEE) received the bachelor’s and master’s degrees from Northeastern University, Shenyang, China, in 2009 and 2011, respectively, and the Ph.D. degree from the Department of Electrical and Electronic Engineering, Imperial College London, London, U.K., in 2015.
He has been a Research Staff Member with IBM T. J. Watson Research Center, Yorktown Heights, NY, USA, since 2016, where he was also a Graduate...Show More
Shiqiang Wang (Member, IEEE) received the bachelor’s and master’s degrees from Northeastern University, Shenyang, China, in 2009 and 2011, respectively, and the Ph.D. degree from the Department of Electrical and Electronic Engineering, Imperial College London, London, U.K., in 2015.
He has been a Research Staff Member with IBM T. J. Watson Research Center, Yorktown Heights, NY, USA, since 2016, where he was also a Graduate...View more
Author image of Jian Li
Department of Electrical and Computer Engineering, Binghamton University, State University of New York, Binghamton, NY, USA
Jian Li (Member, IEEE) received the B.E. degree from Shanghai Jiao Tong University, Shanghai, China, in June 2012, and the Ph.D. degree in computer engineering from Texas A&M University at College Station, College Station, TX, USA, in December 2016.
He is an Assistant Professor of Computer Engineering with the Department of Electrical and Computer Engineering, State University of New York, Binghamton University, Binghamton...Show More
Jian Li (Member, IEEE) received the B.E. degree from Shanghai Jiao Tong University, Shanghai, China, in June 2012, and the Ph.D. degree in computer engineering from Texas A&M University at College Station, College Station, TX, USA, in December 2016.
He is an Assistant Professor of Computer Engineering with the Department of Electrical and Computer Engineering, State University of New York, Binghamton University, Binghamton...View more
Author image of M. Hadi Amini
Knight Foundation School of Computing and Information Sciences and the Sustainability, Optimization, and Learning for Interdependent Networks Laboratory, Florida International University, Miami, FL, USA
M. Hadi Amini (Member, IEEE) received the B.Sc. degree from Sharif University of Technology, Tehran, Iran, in 2011, the M.Sc. degree from Tarbiat Modares University, Tehran, in 2013, the M.Sc. and Ph.D. degrees in electrical and computer engineering from Carnegie Mellon University, Pittsburgh, PA, USA, in 2015 and 2019, respectively, and the Doctoral degree in computer science and technology from SYSU, Guangzhou, China, i...Show More
M. Hadi Amini (Member, IEEE) received the B.Sc. degree from Sharif University of Technology, Tehran, Iran, in 2011, the M.Sc. degree from Tarbiat Modares University, Tehran, in 2013, the M.Sc. and Ph.D. degrees in electrical and computer engineering from Carnegie Mellon University, Pittsburgh, PA, USA, in 2015 and 2019, respectively, and the Doctoral degree in computer science and technology from SYSU, Guangzhou, China, i...View more
Contents

I. Introduction

In this section, we explain the motivation to conduct a comprehensive survey on federated learning (FL) for resource-constrained Internet-of-Things (IoT) devices, followed by recently published prior works, and differentiate how our proposed survey is necessary for the FL domain. After that, we discuss our contributions and the necessity of conducting this research. Finally, at the end of this section, we briefly highlight the organization of this article.

Author image of Ahmed Imteaj
Knight Foundation School of Computing and Information Sciences and the Sustainability, Optimization, and Learning for Interdependent Networks Laboratory, Florida International University, Miami, FL, USA
Ahmed Imteaj received the B.Sc. degree in computer science and engineering from Chittagong University of Engineering and Technology, Chittagong, Bangladesh, in 2015. He is currently pursuing the Ph.D. degree with Florida International University, Miami, FL, USA.
He is a Graduate Assistant with the Knight Foundation School of Computing and Information Sciences, Florida International University, where he is also a Research Lab Member with the Sustainability, Optimization, and Learning for Interdependent Networks Laboratory. From 2015 to 2018, he worked as a Lecturer with International Islamic University Chittagong, Chittagong. He has published more than 30 referred journals and conference papers. His research interests span federated learning, Internet of Things (IoT), machine learning, blockchain, sensor networks, cyber–physical–social resilience, and optimization.
Mr. Imteaj’s work on federated learning for IoT environments was a recipient of the Best Paper Award from the “2019 IEEE Conference on Computational Science and Computational Intelligence” and won the Second Place at 2021 Florida International University GSAW Scholarly Forum. (Lab website: http://www.solidlab.network).
Ahmed Imteaj received the B.Sc. degree in computer science and engineering from Chittagong University of Engineering and Technology, Chittagong, Bangladesh, in 2015. He is currently pursuing the Ph.D. degree with Florida International University, Miami, FL, USA.
He is a Graduate Assistant with the Knight Foundation School of Computing and Information Sciences, Florida International University, where he is also a Research Lab Member with the Sustainability, Optimization, and Learning for Interdependent Networks Laboratory. From 2015 to 2018, he worked as a Lecturer with International Islamic University Chittagong, Chittagong. He has published more than 30 referred journals and conference papers. His research interests span federated learning, Internet of Things (IoT), machine learning, blockchain, sensor networks, cyber–physical–social resilience, and optimization.
Mr. Imteaj’s work on federated learning for IoT environments was a recipient of the Best Paper Award from the “2019 IEEE Conference on Computational Science and Computational Intelligence” and won the Second Place at 2021 Florida International University GSAW Scholarly Forum. (Lab website: http://www.solidlab.network).View more
Author image of Urmish Thakker
Deep Learning Research, SambaNova Systems, Palo Alto, CA, USA
Urmish Thakker received the bachelor’s degree from Birla Institute of Technology and Science Pilani, Pilani, India, in 2012, and the master’s degree in computer science from UW Madison, Madison, WI, USA.
He is a Deep Learning Researcher with SambaNova Systems, Palo Alto, CA, USA. Before joining SambaNova, he worked with Arm Research, Texas Instruments and Broadcom, AMD, Santa Clara, CA, USA. Specifically, he has worked on model quantization, pruning, structured matrices and low-rank decomposition. His work has led to patents, publications, and contributions to various products across multiple companies. His research has primarily focused on efficient execution of neural networks on resource-constrained devices.
Urmish Thakker received the bachelor’s degree from Birla Institute of Technology and Science Pilani, Pilani, India, in 2012, and the master’s degree in computer science from UW Madison, Madison, WI, USA.
He is a Deep Learning Researcher with SambaNova Systems, Palo Alto, CA, USA. Before joining SambaNova, he worked with Arm Research, Texas Instruments and Broadcom, AMD, Santa Clara, CA, USA. Specifically, he has worked on model quantization, pruning, structured matrices and low-rank decomposition. His work has led to patents, publications, and contributions to various products across multiple companies. His research has primarily focused on efficient execution of neural networks on resource-constrained devices.View more
Author image of Shiqiang Wang
IBM T. J. Watson Research Center, Yorktown Heights, NY, USA
Shiqiang Wang (Member, IEEE) received the bachelor’s and master’s degrees from Northeastern University, Shenyang, China, in 2009 and 2011, respectively, and the Ph.D. degree from the Department of Electrical and Electronic Engineering, Imperial College London, London, U.K., in 2015.
He has been a Research Staff Member with IBM T. J. Watson Research Center, Yorktown Heights, NY, USA, since 2016, where he was also a Graduate-Level Co-Op in the summers of 2014 and 2013. In the fall of 2012, he was with NEC Laboratories Europe, Heidelberg, Germany. His current research focuses on the interdisciplinary areas in distributed computing, machine learning, networking, optimization, and signal processing.
Dr. Wang received the IEEE Communications Society Leonard G. Abraham Prize in 2021, the IBM Outstanding Technical Achievement Award in 2019 and 2021, the multiple Invention Achievement Awards from IBM in 2016, the Best Paper Finalist of the IEEE International Conference on Image Processing 2019, and Best Student Paper Award of the Network and Information Sciences International Technology Alliance in 2015. He served as a Technical Program Committee Member of several international conferences, including ICML, NeurIPS, ICDCS, AISTATS, IJCAI, IFIP Networking, IEEE GLOBECOM, and IEEE ICC and an Associate Editor of the IEEE Transactions on Mobile Computing.
Shiqiang Wang (Member, IEEE) received the bachelor’s and master’s degrees from Northeastern University, Shenyang, China, in 2009 and 2011, respectively, and the Ph.D. degree from the Department of Electrical and Electronic Engineering, Imperial College London, London, U.K., in 2015.
He has been a Research Staff Member with IBM T. J. Watson Research Center, Yorktown Heights, NY, USA, since 2016, where he was also a Graduate-Level Co-Op in the summers of 2014 and 2013. In the fall of 2012, he was with NEC Laboratories Europe, Heidelberg, Germany. His current research focuses on the interdisciplinary areas in distributed computing, machine learning, networking, optimization, and signal processing.
Dr. Wang received the IEEE Communications Society Leonard G. Abraham Prize in 2021, the IBM Outstanding Technical Achievement Award in 2019 and 2021, the multiple Invention Achievement Awards from IBM in 2016, the Best Paper Finalist of the IEEE International Conference on Image Processing 2019, and Best Student Paper Award of the Network and Information Sciences International Technology Alliance in 2015. He served as a Technical Program Committee Member of several international conferences, including ICML, NeurIPS, ICDCS, AISTATS, IJCAI, IFIP Networking, IEEE GLOBECOM, and IEEE ICC and an Associate Editor of the IEEE Transactions on Mobile Computing.View more
Author image of Jian Li
Department of Electrical and Computer Engineering, Binghamton University, State University of New York, Binghamton, NY, USA
Jian Li (Member, IEEE) received the B.E. degree from Shanghai Jiao Tong University, Shanghai, China, in June 2012, and the Ph.D. degree in computer engineering from Texas A&M University at College Station, College Station, TX, USA, in December 2016.
He is an Assistant Professor of Computer Engineering with the Department of Electrical and Computer Engineering, State University of New York, Binghamton University, Binghamton, NY, USA. He was a Postdoctoral Fellow with the College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, MA, USA, from January 2017 to August 2019. His current research interests lie in the areas of reinforcement learning, online learning, network optimization, online algorithms, and their applications in large-scale networked systems.
Jian Li (Member, IEEE) received the B.E. degree from Shanghai Jiao Tong University, Shanghai, China, in June 2012, and the Ph.D. degree in computer engineering from Texas A&M University at College Station, College Station, TX, USA, in December 2016.
He is an Assistant Professor of Computer Engineering with the Department of Electrical and Computer Engineering, State University of New York, Binghamton University, Binghamton, NY, USA. He was a Postdoctoral Fellow with the College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, MA, USA, from January 2017 to August 2019. His current research interests lie in the areas of reinforcement learning, online learning, network optimization, online algorithms, and their applications in large-scale networked systems.View more
Author image of M. Hadi Amini
Knight Foundation School of Computing and Information Sciences and the Sustainability, Optimization, and Learning for Interdependent Networks Laboratory, Florida International University, Miami, FL, USA
M. Hadi Amini (Member, IEEE) received the B.Sc. degree from Sharif University of Technology, Tehran, Iran, in 2011, the M.Sc. degree from Tarbiat Modares University, Tehran, in 2013, the M.Sc. and Ph.D. degrees in electrical and computer engineering from Carnegie Mellon University, Pittsburgh, PA, USA, in 2015 and 2019, respectively, and the Doctoral degree in computer science and technology from SYSU, Guangzhou, China, in 2018.
He is an Assistant Professor with the Knight Foundation School of Computing and Information Sciences, Florida International University, Miami, FL, USA. He is the Director of Sustainability, Optimization, and Learning for InterDependent Networks Laboratory (http://www.solidlab.network). He has published more than 100 refereed journal and conference papers, and book chapters. He has edited/authored six books. His research interests include distributed optimization and learning algorithms, distributed computing and intelligence, sensor networks, interdependent networks, and cyber–physical–social resilience. Application domains include smart cities, energy systems, transportation networks, and healthcare. (Homepage: http://www.hadiamini.com)
Dr. Amini was a recipient of the Best Paper Award from “2019 IEEE Conference on Computational Science and Computational Intelligence,” FIU’s Knight Foundation School of Computing and Information Sciences “Excellence in Teaching Award,” Best Reviewer Award from Four IEEE Transactions, the Best Journal Paper Award in “Journal of Modern Power Systems and Clean Energy,” and the Dean’s Honorary Award from the President of Sharif University of Technology. He has served as the President of Carnegie Mellon University Energy Science and Innovation Club; as technical program committee of several IEEE and ACM conferences; and as the Lead Editor for a book series on Sustainable Interdependent Networks: From Theory to Application in 2017. He also serves as an Associate Editor for SN Operations Research Forum, Frontiers in Communications and Networks (Data Science for Communications), and International Transactions on Electrical Energy Systems. He is a Life Member of IEEE-Eta Kappa Nu (IEEE-HKN), the Honor Society of IEEE. (Lab website: http://www.solidlab.network).
M. Hadi Amini (Member, IEEE) received the B.Sc. degree from Sharif University of Technology, Tehran, Iran, in 2011, the M.Sc. degree from Tarbiat Modares University, Tehran, in 2013, the M.Sc. and Ph.D. degrees in electrical and computer engineering from Carnegie Mellon University, Pittsburgh, PA, USA, in 2015 and 2019, respectively, and the Doctoral degree in computer science and technology from SYSU, Guangzhou, China, in 2018.
He is an Assistant Professor with the Knight Foundation School of Computing and Information Sciences, Florida International University, Miami, FL, USA. He is the Director of Sustainability, Optimization, and Learning for InterDependent Networks Laboratory (http://www.solidlab.network). He has published more than 100 refereed journal and conference papers, and book chapters. He has edited/authored six books. His research interests include distributed optimization and learning algorithms, distributed computing and intelligence, sensor networks, interdependent networks, and cyber–physical–social resilience. Application domains include smart cities, energy systems, transportation networks, and healthcare. (Homepage: http://www.hadiamini.com)
Dr. Amini was a recipient of the Best Paper Award from “2019 IEEE Conference on Computational Science and Computational Intelligence,” FIU’s Knight Foundation School of Computing and Information Sciences “Excellence in Teaching Award,” Best Reviewer Award from Four IEEE Transactions, the Best Journal Paper Award in “Journal of Modern Power Systems and Clean Energy,” and the Dean’s Honorary Award from the President of Sharif University of Technology. He has served as the President of Carnegie Mellon University Energy Science and Innovation Club; as technical program committee of several IEEE and ACM conferences; and as the Lead Editor for a book series on Sustainable Interdependent Networks: From Theory to Application in 2017. He also serves as an Associate Editor for SN Operations Research Forum, Frontiers in Communications and Networks (Data Science for Communications), and International Transactions on Electrical Energy Systems. He is a Life Member of IEEE-Eta Kappa Nu (IEEE-HKN), the Honor Society of IEEE. (Lab website: http://www.solidlab.network).View more

Contact IEEE to Subscribe
More Like This
Joint Optimization of Energy Consumption and Latency in Mobile Edge Computing for Internet of Things

IEEE Internet of Things Journal

Published: 2019

A Decentralized and Trusted Edge Computing Platform for Internet of Things

IEEE Internet of Things Journal

Published: 2020

Show More

References

References is not available for this document.

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.