Abdellah Chehri
ABSTRACT
The rapid adoption of smartphones and the explosive growth of data traffic due to these devices have been phenomenal. As the world anticipates more connected devices — the Internet of Things (IoT), vehicle-to-vehicle (V2V) communications, and wearable devices — and more value-added applications and services (ultra-high-definition video, 360° video, virtual reality, smart cars, etc.), leading industry experts are calling for the sixth generation (6G) networks. Federated learning is a common distributed machine learning framework. Through the training of the global model, the problems of large communication overhead and data privacy protection in traditional centralized machine learning are solved. Federated learning (FL) is essential in optimizing wireless communication networks' resources. On the other hand, wireless communications are crucial for FL. Therefore, the purpose of this survey paper is to bridge this gap in the literature by discussing the interdependency between FL and backhaul wireless communications.
- Liu L., Zhang J., Song S., Letaief K. B., Edge-assisted hierarchical federated learning with non-iid data, arXiv preprint arXiv:1905.06641, 2019.Google Scholar
- Jiang Y., Wang S., Victor V., Jun K., Lee W., Leung K., Leandros T., Model pruning enables efficient federated learning on edge devices, IEEE Transactions on Neural Networks and Learning Systems, 2022.Google Scholar
- Mohammed I., Tabatabai, S. A. Fuqaha, F. Bouanani, J. Qadir, B. Qolomany, M. Guizani. Budgeted online selection of candidate IoT clients to participate in federated learning, IEEE Internet of Things Journal, VOL. 7, NO. 8, pp. 5938-5952, 2020.Google Scholar
- Wang L., Wang W., Li B.. CMFL: Mitigating communication overhead for federated learning, IEEE 39th international conference on distributed computing systems, ICDCS, pp. 954-964, 2019Google ScholarCross Ref
- Ping-Heng Kuo and Mourad A., Millimeter wave for 5G mobile fronthaul and backhaul, 2017 European Conference on Networks and Communications (EuCNC), 2017, pp. 1-5, doi: 10.1109/EuCNC.2017.7980750.Google ScholarCross Ref
- Bande M. and Veeravalli V. V., Design of a Heterogeneous Cellular Network with a Wireless Backhaul, in IEEE Transactions on Wireless Communications, vol. 20, no. 1, pp. 243-253, Jan. 2021.Google ScholarDigital Library
- Chehri A. and Mouftah H. T., New MMSE Downlink Channel Estimation for Sub-6 GHz Non-Line-of-Sight Backhaul, 2018 IEEE Globecom Workshops (GC Wkshps), 2018, pp. 1-7.Google ScholarCross Ref
- Chehri A. and Mouftah H. T., PHY-MAC MIMO Precoder Design for Sub-6 GHz Backhaul Small Cell, 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), 2020, pp. 1-5.Google ScholarCross Ref
- Su X. and Chang K., A comparative study on wireless backhaul solutions for beyond 4G network, The International Conference on Information Networking 2013 (ICOIN), 2013, pp. 505-51Google ScholarDigital Library
- Yang, Y.; Hong, Y.; Park, J. Efficient Gradient Updating Strategies with Adaptive Power Allocation for Federated Learning over Wireless Backhaul. Sensors 2021, 21, 6791. https://doi.org/10.3390/s21206791Google ScholarCross Ref
- Lin Z., Li X., Lau V. K. N., Gong Y. and Huang K., Deploying Federated Learning in Large-Scale Cellular Networks: Spatial Convergence Analysis, in IEEE Transactions on Wireless Communications, vol. 21, no. 3, pp. 1542-1556, March 2022, doi: 10.1109/TWC.2021.3104834.Google ScholarCross Ref
- Niknam S., Dhillon H. S. and Reed J. H., "Federated Learning for Wireless Communications: Motivation, Opportunities, and Challenges, in IEEE Communications Magazine, vol. 58, no. 6, pp. 46-51, June 2020, doi: 10.1109/MCOM.001.1900461.Google ScholarCross Ref
- Vu T. T., Ngo D. T., Tran N. H., Ngo H. Q., Dao M. N. and Middleton R. H., Cell-Free Massive MIMO for Wireless Federated Learning, in IEEE Transactions on Wireless Communications, vol. 19, no. 10, pp. 6377-6392, Oct. 2020, doi: 10.1109/TWC.2020.3002988.Google ScholarCross Ref
- Chehri A., Utility-Based Beam Selection Algorithms for Sub-6 GHz Backhauls, 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (AP-S/URSI), 2022, pp. 1682-1683, doi: 10.1109/AP-S/USNC-URSI47032.2022.9886616.Google ScholarCross Ref
Index Terms
- Fed-Haul: A Federated Learning Dual Band Point Multi-Point Backhaul Requirements in 5G Evolution and Beyond
Recommendations
Blockchain management and machine learning adaptation for IoT environment in 5G and beyond networks: A systematic review
AbstractKeeping in view of the constraints and challenges with respect to big data analytics along with security and privacy preservation for 5G and B5G applications, the integration of machine learning and blockchain, two of the most ...
Federated Machine Learning In 5G Smart Healthcare: A Security Perspective Review
AbstractFederated learning (also known as collaborative learning) is a decentralized approach to training machine learning models. In 5G smart healthcare, federated machine learning (FML) can potentially improve patient care by offering improved diagnosis,...
5G: The Convergence of Wireless Communications
As the rollout of 4G mobile communication networks takes place, representatives of industry and academia have started to look into the technological developments toward the next generation (5G). Several research projects involving key international ...
Comments