Over-the-Air Federated Averaging with Limited Power and Privacy Budgets

To jointly overcome the communication bottleneck and privacy leakage of wireless federated learning (FL), this paper studies a differentially private over-the-air federated averaging (DP-OTA-FedAvg) system with a limited sum power budget. With DP-OTA-FedAvg, the gradients are aligned by an alignment coefficient and aggregated over the air, and channel noise is employed to protect privacy. We aim to improve the learning performance by jointly designing the device scheduling, alignment coefficient, and the number of aggregation rounds of federated averaging (FedAvg) subject to sum power and privacy constraints. We first present the privacy analysis based on differential privacy (DP) to quantify the impact of the alignment coefficient on privacy preservation in each communication round. Furthermore, to study how the device scheduling, alignment coefficient, and the number of the global aggregation affect the learning process, we conduct the convergence analysis of DP-OTA-FedAvg in the cases of convex and non-convex loss functions. Based on these analytical results, we formulate an optimization problem to minimize the optimality gap of the DP-OTA-FedAvg subject to limited sum power and privacy budgets. The problem is solved by decoupling it into two sub-problems. Given the number of communication rounds, we conclude the relationship between the number of scheduled devices and the alignment coefficient, which offers a set of potential optimal solution pairs of device scheduling and the alignment coefficient. Thanks to the reduced search space, the optimal solution can be efficiently obtained. The effectiveness of the proposed policy is validated through simulations.

Performance Analysis and Low-Complexity Design for XL-MIMO with Near-Field Spatial Non-Stationarities

Extremely large-scale multiple-input multiple-output (XL-MIMO) is capable of supporting extremely high system capacities with large numbers of users. In this work, we build a framework for the analysis and low-complexity design of XL-MIMO in the near-field with spatial non-stationarities. Specifically, we first analyze the theoretical performance of discrete-aperture XL-MIMO using an electromagnetic (EM) channel model based on the near-field spherical wave-front. We analytically unveil the impact of the discrete aperture and polarization mismatch on the received power. We also review the amplitude-aware Fraunhofer distance based on the considered EM channel model. Our analytical results indicate that a limited part of the XL-array receives the majority of the signal power in the near-field, which leads to a notion of visibility region (VR) of a user. Thus, we propose a VR detection algorithm and exploit the acquired VR information to design a low-complexity symbol detection scheme. Furthermore, we propose a graph theory-based user partition algorithm, relying on the VR overlap ratio between different users. Partial zero-forcing (PZF) is utilized to eliminate only the interference from users allocated to the same group, which further reduces computational complexity in matrix inversion. Numerical results confirm the correctness of the analytical results and the effectiveness of the proposed algorithms. It reveals that our algorithms approach the performance of conventional whole array (WA)-based designs but with much lower complexity.

Device Scheduling for Over-the-Air Federated Learning with Differential Privacy

In this paper, we propose a device scheduling scheme for differentially private over-the-air federated learning (DP-OTA-FL) systems, referred to as S-DPOTAFL, where the privacy of the participants is guaranteed by channel noise. In S-DPOTAFL, the gradients are aligned by the alignment coefficient and aggregated via over-the-air computation (AirComp). The scheme schedules the devices with better channel conditions in the training to avoid the problem that the alignment coefficient is limited by the device with the worst channel condition in the system. We conduct the privacy and convergence analysis to theoretically demonstrate the impact of device scheduling on privacy protection and learning performance. To improve the learning accuracy, we formulate an optimization problem with the goal to minimize the training loss subjecting to privacy and transmit power constraints. Furthermore, we present the condition that the S-DPOTAFL performs better than the DP-OTA-FL without considering device scheduling (NoS-DPOTAFL). The effectiveness of the S-DPOTAFL is validated through simulations.

Toward Secure and Private Over-the-Air Federated Learning

In this paper, a novel secure and private over-the-air federated learning (SP-OTA-FL) framework is studied where noise is employed to protect data privacy and system security. Specifically, the privacy leakage of user data and the security level of the system are measured by differential privacy (DP) and mean square error security (MSE-security), respectively. To mitigate the impact of noise on learning accuracy, we propose a channel-weighted post-processing (CWPP) mechanism, which assigns a smaller weight to the gradient of the device with poor channel conditions. Furthermore, employing CWPP can avoid the issue that the signal-to-noise ratio (SNR) of the overall system is limited by the device with the worst channel condition in aligned over-the-air federated learning (OTA-FL). We theoretically analyze the effect of noise on privacy and security protection and also illustrate the adverse impact of noise on learning performance by conducting convergence analysis. Based on these analytical results, we propose device scheduling policies considering privacy and security protection in different cases of channel noise. In particular, we formulate an integer nonlinear fractional programming problem aiming to minimize the negative impact of noise on the learning process. We obtain the closed-form solution to the optimization problem when the model is with high dimension. For the general case, we propose a secure and private algorithm (SPA) based on the branch-and-bound (BnB) method, which can obtain an optimal solution with low complexity. The effectiveness of the proposed CWPP mechanism and the policies for device selection are validated through simulations.

Active RIS Versus Passive RIS: Which Is Superior with the Same Power Budget?

This letter theoretically compares the active reconfigurable intelligent surface (RIS)-aided system with the passive RIS-aided system. For fair comparison, we consider that these two systems have the same overall power budget that can be used at both the base station (BS) and the RIS. For active RIS, we first derive the optimal power allocation between the BS's transmit signal power and RIS's output signal power. We also analyze the impact of various system parameters on the optimal power allocation ratio. Then, we compare the performance between the active RIS and the passive RIS, which demonstrates that the active RIS would be superior if the power budget is not very small and the number of RIS elements is not very large.

Meta-learning for RIS-assisted NOMA Networks

A novel reconfigurable intelligent surfaces (RISs)-based transmission framework is proposed for downlink non-orthogonal multiple access (NOMA) networks. We propose a quality-of-service (QoS)-based clustering scheme to improve the resource efficiency and formulate a sum rate maximization problem by jointly optimizing the phase shift of the RIS and the power allocation at the base station (BS). A model-agnostic meta-learning (MAML)-based learning algorithm is proposed to solve the joint optimization problem with a fast convergence rate and low model complexity. Extensive simulation results demonstrate that the proposed QoS-based NOMA network achieves significantly higher transmission throughput compared to the conventional orthogonal multiple access (OMA) network. It can also be observed that substantial throughput gain can be achieved by integrating RISs in NOMA and OMA networks. Moreover, simulation results of the proposed QoS-based clustering method demonstrate observable throughput gain against the conventional channel condition-based schemes.