In this work, hierarchical federated learning (HFL) over wireless multi-cell networks is proposed for large-scale model training while preserving data privacy. However, the imbalanced data distribution has a significant impact on the convergence rate and learning accuracy. In addition, a large learning latency is incurred due to the traffic load imbalance among base stations (BSs) and limited wireless resources. To cope with these challenges, we first provide an analysis of the model error and learning latency in wireless HFL. Then, joint user association and wireless resource allocation algorithms are investigated under independent identically distributed (IID) and non-IID training data, respectively. For the IID case, a learning latency aware strategy is designed to minimize the learning latency by optimizing user association and wireless resource allocation, where a mobile device selects the BS with the maximal uplink channel signal-to-noise ratio (SNR). For the non-IID case, the total data distribution distance and learning latency are jointly minimized to achieve the optimal user association and resource allocation. The results show that both data distribution and uplink channel SNR should be taken into consideration for user association in the non-IID case. Finally, the effectiveness of the proposed algorithms are demonstrated by the simulations.

In recent years, wireless federated learning (FL) has been proposed to support the mobile intelligent applications over the wireless network, which protects the data privacy and security by exchanging the parameter between mobile devices and the base station (BS). However, the learning latency increases with the neural network scale due to the limited local computing power and communication bandwidth. To tackle this issue, we introduce model pruning for wireless FL to reduce the neural network scale. Device selection is also considered to further improve the learning performance. By removing the stragglers with low computing power or bad channel condition, the model aggregation loss caused by model pruning can be alleviated and the communication overhead can be effectively reduced. We analyze the convergence rate and learning latency of the proposed model pruning method and formulate an optimization problem to maximize the convergence rate under the given learning latency budget via jointly optimizing the pruning ratio, device selection, and wireless resource allocation. By solving the problem, the closed-form solutions of pruning ratio and wireless resource allocation are derived and the threshold-based device selection strategy is developed. Finally, extensive experiments are carried out to demonstrate that the proposed model pruning algorithm outperforms other existing schemes.

The botnet, as one of the most formidable threats to cyber security, is often used to launch large-scale attack sabotage. How to accurately identify the botnet, especially to improve the performance of the detection model, is a key technical issue. In this paper, we propose a framework based on generative adversarial networks to augment botnet detection models (Bot-GAN). Moreover, we explore the performance of the proposed framework based on flows. The experimental results show that Bot-GAN is suitable for augmenting the original detection model. Compared with the original detection model, the proposed approach improves the detection performance, and decreases the false positive rate, which provides an effective method for improving the detection performance. In addition, it also retains the primary characteristics of the original detection model, which does not care about the network payload information, and has the ability to detect novel botnets and others using encryption or proprietary protocols.

In this letter, we apply the model compression, i.e., network pruning, into wireless federated learning (FL) system to mitigate the local computation and communication bottlenecks. Firstly, the convergence rate and learning latency of the FL system are mathematically analyzed. Then, an optimization problem is formulated to maximize the convergence rate while guaranteeing the learning latency via jointly optimizing the pruning ratio and spectrum allocation. Finally, the experimental results show that the proposed learning scheme can improve the performance of the wireless FL as compared with other conventional schemes.

In Federated Edge Learning (FEEL) networks, edge devices exchange the model parameters with each other to protect data privacy, instead of directly transmitting data samples. However, the learning performance may decrease due to the limited computation, communication, and storage resources. On the one hand, devices may not have sufficient storage for the redundant data samples. On the other hand, the model transmission and computation cause a large training latency. To address these issues, we develop a storage-aware user scheduling and bandwidth allocation Federated Learning (FL) algorithm with data cleansing by taking into consideration the storage resource, data influence, and channel state information. First, a data influence evaluation method is introduced by analyzing the model divergence in a communication round aroused by the data sample. Secondly, a probability-based user scheduling scheme is proposed by minimizing the weighted sum of the storage consumption, data influence, and uploading latency. Accordingly, the joint user scheduling and bandwidth allocation scheme is developed to minimize the maximum latency for local gradient uploading. Extensive experiments demonstrate that the proposed algorithm can significantly reduce the storage pressure and the training latency while improving the learning accuracy.

Recently, deep learning (DL) based semantic communication systems have shown great potential to improve transmission efficiency in various tasks. However, the coexisting mechanism between semantic communications and other services remains unexplored, which limits the application of semantic communications in practical communication systems. In this paper, we propose a dynamic multiplexing and co-scheduling scheme for the semantic and ultra-reliable low-latency communication (URLLC) traffic coexisting systems. In particular, a joint resource allocation and model training problem is formulated, which aims at maximizing the utility of semantic service while satisfying the latency requirement of URLLC traffic. To reduce the computational complexity, the original problem is simplified and decoupled into a joint resource allocation and model selection problem and a robust model training problem. In the resource allocation and model selection phase, the original problem is decomposed into three subproblems and an alternating optimization algorithm is then proposed to obtain the optimal resource allocation result. In the model training phase, a two-stage semantic communication network is designed, which can efficiently mitigate the impact of feature erasure brought by the random arrival of URLLC traffic. Simulation results show that the proposed method can effectively improve the quality of semantic service while satisfying the latency requirement of URLLC traffic.