Massive MIMO for Serving Federated Learning and Non-Federated Learning Users
Uloženo v:
| Název: | Massive MIMO for Serving Federated Learning and Non-Federated Learning Users |
|---|---|
| Autoři: | Farooq, Muhammad, Vu, Thanh Tung, Ngo, Hien Quoc, Tran, Le-Nam |
| Zdroj: | IEEE Transactions on Wireless Communications. 23(1):247-262 |
| Témata: | Massive multiple-input multiple-output (MIMO), federated learning (FL), resource allocation, successive convex approximation (SCA) |
| Popis: | With its privacy preservation and communication efficiency, federated learning (FL) has emerged as a promising learning framework for beyond 5G wireless networks. It is anticipated that future wireless networks will jointly serve both FL and downlink non-FL user groups in the same time-frequency resource. While in the downlink of each FL iteration, both groups simultaneously receive data from the base station in the same time-frequency resource, the uplink of each FL iteration requires bidirectional communication to support uplink transmission for FL users and downlink transmission for non-FL users. To overcome this challenge, we present half-duplex (HD) and full-duplex (FD) communication schemes to serve both groups. More specifically, we adopt the massive multiple-input multiple-output technology and aim to maximize the minimum effective rate of non-FL users under a quality of service (QoS) latency constraint for FL users. Since the formulated problem is nonconvex, we propose a power control algorithm based on successive convex approximation to find a stationary solution. Numerical results show that the proposed solutions perform significantly better than the considered baselines schemes. Moreover, the FD-based scheme outperforms the HD-based counterpart in scenarios where the self-interference is small or moderate and/or the size of FL model updates is large. |
| Popis souboru: | electronic |
| Přístupová URL adresa: | https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-201005 https://liu.diva-portal.org/smash/get/diva2:1840093/FULLTEXT01.pdf |
| Databáze: | SwePub |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | With its privacy preservation and communication efficiency, federated learning (FL) has emerged as a promising learning framework for beyond 5G wireless networks. It is anticipated that future wireless networks will jointly serve both FL and downlink non-FL user groups in the same time-frequency resource. While in the downlink of each FL iteration, both groups simultaneously receive data from the base station in the same time-frequency resource, the uplink of each FL iteration requires bidirectional communication to support uplink transmission for FL users and downlink transmission for non-FL users. To overcome this challenge, we present half-duplex (HD) and full-duplex (FD) communication schemes to serve both groups. More specifically, we adopt the massive multiple-input multiple-output technology and aim to maximize the minimum effective rate of non-FL users under a quality of service (QoS) latency constraint for FL users. Since the formulated problem is nonconvex, we propose a power control algorithm based on successive convex approximation to find a stationary solution. Numerical results show that the proposed solutions perform significantly better than the considered baselines schemes. Moreover, the FD-based scheme outperforms the HD-based counterpart in scenarios where the self-interference is small or moderate and/or the size of FL model updates is large. |
|---|---|
| ISSN: | 15361276 15582248 |
| DOI: | 10.1109/TWC.2023.3277037 |