Data heterogeneity may significantly deteriorate the performance of federated learning since the client’s data distribution is divergent. To mitigate this issue, an effective method is to partition these clients into suitable clusters. However, existing clustered federated learning is only based on the gradient descent method, which leads to poor convergence performance. To accelerate the convergence rate, this paper proposes clustered federated learning based on momentum gradient descent (CFL-MGD) by integrating momentum and cluster techniques. In CFL-MGD, scattered clients are partitioned into the same cluster when they have the same learning tasks. Meanwhile, each client in the same cluster utilizes their own private data to update local model parameters through the momentum gradient descent. Moreover, we present gradient averaging and model averaging for global aggregation, respectively. To understand the proposed algorithm, we also prove that CFL-MGD converges at an exponential rate for smooth and strongly convex loss functions. Finally, we validate the effectiveness of CFL-MGD on CIFAR-10 and MNIST datasets.

Semantic communication (SC) is one of the promising solutions for future wireless communications due to its superior transmission efficiency. However, the semantic information cannot be transmitted accurately under noisy channels by the existing methods. For this reason, we propose a fairness-based transmission strategy for STAR-RIS assisted SC systems. On this basis, we investigate two operating protocols of STAR-RIS, energy splitting (ES) and mode switching (MS). More specifically, we maximize the minimum signal-to-noise ratio (SNR) of the users by jointly optimizing the active beamforming and the passive beamforming under the constraint of limited power at the base station (BS). To tackle this max-min optimization problem, for ES, we develop a double-loop iterative algorithm by using the successive convex approximation (SCA) and penalty function methods. For MS protocol, we further add an additional penalty in the objective function to address the optimization problem. Moreover, we rigorously prove that the proposed algorithm can converge to a locally optimal solution. At last, we conduct various experiments to verify the performance of the proposed algorithms. Simulation experiments demonstrate that our algorithm outperforms other benchmark methods in fairness and semantic similarity.

Federated learning has become a prevalent distributed training paradigm, in which local devices collaboratively train learning models without exchanging local data. One of the most dominant frameworks of federated learning (FL) is FedAvg, since it is efficient and simple to implement; here, the first-order information is generally utilized to train the parameters of learning models. In practice, however, the gradient information may be unavailable or infeasible in some applications, such as federated black-box optimization problems. To solve the issue, we propose an innovative zeroth-order adaptive federated learning algorithm without using the gradient information, referred to as ZO-AdaFL, which integrates the zeroth-order optimization algorithm into the adaptive gradient method. Moreover, we also rigorously analyze the convergence behavior of ZO-AdaFL in a non-convex setting, i.e., where ZO-AdaFL achieves convergence to a region close to a stationary point at a speed of $O(1/T)$ (T represents the total iteration number). Finally, to verify the performance of ZO-AdaFL, simulation experiments are performed using the MNIST and FMNIST datasets. Our experimental findings demonstrate that ZO-AdaFL outperforms other state-of-the-art zeroth-order FL approaches in terms of both effectiveness and efficiency.

In federated learning (FL), model parameters of deep learning are communicated between clients and the central server. To better train deep learning models, the spectrum resource and transmission security need to be guaranteed. Toward this end, we propose a secrecy transmission protocol based on energy harvesting and jammer selection for FL, in which the secondary transmitters can harvest energy from the primary source. Specifically, a secondary transmitter ${\mathrm{ST}}_i$ is first selected, which can offer the best transmission performance for the secondary users to access the primary frequency spectrum. Then, another secondary transmitter ${\mathrm{ST}}_n$, which has the best channel for eavesdropping, is also chosen as a friendly jammer to provide secrecy service. Furthermore, we use outage probability (OP) and intercept probability (IP) as metrics to evaluate performance. Meanwhile, we also derive closed-form expressions of OP and IP of primary users and OP of secondary users for the proposed protocol, respectively. We also conduct a theoretical analysis of the optimal secondary transmission selection (OSTS) protocol. Finally, the performance of the proposed protocol is validated through numerical experiments. The results show that the secrecy performance of the proposed protocol is better than the OSTS and OCJS, respectively.