Federated Learning in Wireless Networks via Over-the-Air Computations
This work addresses efficiency and privacy challenges in federated learning for multi-agent systems in wireless networks, offering an incremental improvement over existing approaches.
The paper tackles the problem of improving efficiency and privacy in federated learning over wireless networks by using Over-the-Air Computation without reconstructing channel coefficients, resulting in enhanced resource savings and privacy guarantees compared to state-of-the-art methods.
In a multi-agent system, agents can cooperatively learn a model from data by exchanging their estimated model parameters, without the need to exchange the locally available data used by the agents. This strategy, often called federated learning, is mainly employed for two reasons: (i) improving resource-efficiency by avoiding to share potentially large datasets and (ii) guaranteeing privacy of local agents' data. Efficiency can be further increased by adopting a beyond-5G communication strategy that goes under the name of Over-the-Air Computation. This strategy exploits the interference property of the wireless channel. Standard communication schemes prevent interference by enabling transmissions of signals from different agents at distinct time or frequency slots, which is not required with Over-the-Air Computation, thus saving resources. In this case, the received signal is a weighted sum of transmitted signals, with unknown weights (fading channel coefficients). State of the art papers in the field aim at reconstructing those unknown coefficients. In contrast, the approach presented here does not require reconstructing channel coefficients by complex encoding-decoding schemes. This improves both efficiency and privacy.