How Does Cell-Free Massive MIMO Support Multiple Federated Learning Groups?

Federated learning (FL) has been considered as a promising learning framework for future machine learning systems due to its privacy preservation and communication efficiency. In beyond-5G/6G systems, it is likely to have multiple FL groups with different learning purposes. This scenario leads to a question: How does a wireless network support multiple FL groups? As an answer, we first propose to use a cell-free massive multiple-input multiple-output (MIMO) network to guarantee the stable operation of multiple FL processes by letting the iterations of these FL processes be executed together within a large-scale coherence time. We then develop a novel scheme that asynchronously executes the iterations of FL processes under multicasting downlink and conventional uplink transmission protocols. Finally, we propose a simple/low-complexity resource allocation algorithm which optimally chooses the power and computation resources to minimize the execution time of each iteration of each FL process.

[1]  Solmaz Niknam,et al.  Federated Learning for Wireless Communications: Motivation, Opportunities, and Challenges , 2019, IEEE Communications Magazine.

[2]  Hien Quoc Ngo,et al.  On the Performance of Multigroup Multicast Cell-Free Massive MIMO , 2017, IEEE Communications Letters.

[3]  Albert Y. Zomaya,et al.  Federated Learning over Wireless Networks: Optimization Model Design and Analysis , 2019, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications.

[4]  Erik G. Larsson,et al.  Cell-Free Massive MIMO Versus Small Cells , 2016, IEEE Transactions on Wireless Communications.

[5]  Walid Saad,et al.  A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks , 2021, IEEE Transactions on Wireless Communications.

[6]  Gordon P. Wright,et al.  Technical Note - A General Inner Approximation Algorithm for Nonconvex Mathematical Programs , 1978, Oper. Res..

[7]  Deniz Gündüz,et al.  Federated Learning Over Wireless Fading Channels , 2019, IEEE Transactions on Wireless Communications.

[8]  Emil Björnson,et al.  Making Cell-Free Massive MIMO Competitive With MMSE Processing and Centralized Implementation , 2019, IEEE Transactions on Wireless Communications.

[9]  Xin Qin,et al.  FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare , 2019, IEEE Intelligent Systems.

[10]  Yao Zhang,et al.  Max-Min Power Optimization in Multigroup Multicast Cell-Free Massive MIMO , 2019, 2019 IEEE Wireless Communications and Networking Conference (WCNC).

[11]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[12]  Hien Quoc Ngo,et al.  Cell-Free Massive MIMO for Wireless Federated Learning , 2019, IEEE Transactions on Wireless Communications.