Semantic communication is envisioned as a promising solution for tackling the data transmission challenges in future wireless communication systems. In this paper, we propose a novel semantic importance-enhanced multi-hop semantic communication (SIMSC) framework that integrates semantic communication with a map-and-forward (MF) relaying scheme. To enhance transmission reliability, the framework employs a semantic importance (SI) calculation module to aid in training joint source-channel coding (JSCC) with relays, thereby better protecting the delivery of crucial semantic information over wireless channels with long-distance signal propagation. Different from conventional amplify-and-forward (AF) and decode-and-forward (DF) relaying schemes, the proposed MF scheme leverages a deep neural network (DNN) to adaptively transform the received signal, optimizing it for multi-hop transmission. This enhances robustness and flexibility in varying relay conditions. Numerical results demonstrate that the proposed SIMSC framework performs notably better than conventional solutions that do not utilize semantic coding or relays. Moreover, the MF relaying scheme outperforms the AF and DF schemes, especially when relay distances vary across hops.

The development of polarization-adjusted convolutional (PAC) codes has introduced a class of efficient designs for short packet transmission. In this contribution, aiming at more flexible code length and rate matching for time-varying channel scenarios, a low-complexity puncturing algorithm for PAC codes is proposed. Specifically, we introduce a Gaussian approximation (GA) algorithm for PAC codes and propose a GA-based optimization method for punctured patterns. Building on this, we present a Gaussian inverse mapping method based on partial order, utilizing a recursive approach to construct the initial set, which significantly reduces the search complexity. Subsequently, we develop a recursive puncturing algorithm based on partial order. Finally, we integrate this method with Reed-Muller (RM) rules, further reducing the complexity.

Federated Learning (FL) enables clients to share model parameters instead of raw data, reducing communication overhead. Traditional wireless networks, however, suffer from latency issues when supporting FL. Cell-Free Massive MIMO (CFmMIMO) offers a promising alternative, as it can serve multiple clients simultaneously on shared resources, enhancing spectral efficiency and reducing latency in large-scale FL. Still, communication resource constraints at the client side can impede the completion of FL training. To tackle this issue, we propose a low-latency, energy-efficient FL framework with optimized uplink power allocation for efficient uplink communication. Our approach integrates an adaptive quantization strategy that dynamically adjusts bit allocation for local gradient updates, significantly lowering communication cost. We formulate a joint optimization problem involving FL model updates, local iterations, and power allocation. This problem is solved using sequential quadratic programming (SQP) to balance energy consumption and latency. Moreover, for local model training, clients employ the AdaDelta optimizer, which improves convergence compared to standard SGD, Adam, and RMSProp. We also provide a theoretical analysis of FL convergence under AdaDelta. Numerical results demonstrate that, under equal energy and latency budgets, our power allocation strategy improves test accuracy by up to 7% and 19% compared to Dinkelbach and max-sum rate approaches. Furthermore, across all power allocation methods, our quantization scheme outperforms AQUILA and LAQ, increasing test accuracy by up to 36% and 35%, respectively.

In the global navigation satellite system (GNSS), identifying not only single but also compound jamming signals is crucial for ensuring reliable navigation and positioning, particularly in future wireless communication scenarios such as the space-air-ground integrated network (SAGIN). However, conventional techniques often struggle with low recognition accuracy and high computational complexity, especially under low jamming-to-noise ratio (JNR) conditions. To overcome the challenge of accurately identifying compound jamming signals embedded within GNSS signals, we propose ACSNet, a novel convolutional neural network designed specifically for this purpose. Unlike conventional methods that tend to exhibit lower accuracy and higher computational demands, particularly in low JNR environments, ACSNet addresses these issues by integrating asymmetric convolution blocks, which improve sensitivity to subtle signal variations while reducing the number of parameters by approximately 50% compared to symmetric convolutional designs. Simulations demonstrate that ACSNet significantly improves accuracy in low JNR regions and shows robust resilience to power ratio (PR) variations. It achieves an overall accuracy of 91.84% and a Kappa coefficient (×100) of 90.82, and notably reaches near 100% recognition accuracy when the JNR is greater than or equal to −9 dB, confirming its effectiveness and efficiency for practical GNSS interference management applications.

With the burgeon deployment of the fifth-generation new radio (5 G NR) networks, the codebook plays a crucial role in enabling the base station (BS) to acquire the channel state information (CSI). Different 5 G NR codebooks incur varying overheads and exhibit performance disparities under diverse channel conditions, necessitating codebook adaptation based on channel conditions to reduce feedback overhead while enhancing performance. However, existing methods of 5 G NR codebooks adaptation require significant overhead for model training and feedback or fall short in performance. To address these limitations, this letter introduces a federated reservoir computing framework designed for efficient codebook adaptation in computationally and feedback resource-constrained mobile devices. This framework utilizes a novel series of indicators as input training data, striking an effective balance between performance and feedback overhead. Compared to conventional models, the proposed codebook adaptation via federated reservoir computing (CA-FedRC), achieves rapid convergence and significant loss reduction in both speed and accuracy. Extensive simulations under various channel conditions demonstrate that our algorithm not only reduces resource consumption of users but also accurately identifies channel types, thereby optimizing the trade-off between spectrum efficiency, computational complexity, and feedback overhead.

With the rapid development of the Internet of Things (IoT), the number of connected devices has increased exponentially, bringing significant convenience to various aspects of daily life and business operations. However, communication between IoT devices requires a significant amount of bandwidth, putting a strain on the communication system. To address this challenge, we introduce a classification-oriented semantic communication approach that transmits only essential information. We present a novel end-to-end task-oriented semantic communication model, which efficiently serves the classification task at the receiver. In particular, the proposed model first utilizes a neural network-based semantic encoder to extract classification-related semantic features. A transformer-based semantic decoder is used at the receiver to retrieve semantic features and generate classification results. We further introduce a channel encoder and decoder module to improve the ability of a single model to deal with various channel conditions. Simulation results show that, compared with the traditional method, the proposed scheme achieves higher classification accuracy on the ESC-50 dataset and UrbanSound8K dataset and has better performance for various channel conditions.

To enhance straggler resilience in federated learning (FL) systems, a semi-decentralized approach has been recently proposed, enabling collaboration between clients. Unlike the existing semi-decentralized schemes, which adaptively adjust the collaboration weight according to the network topology, this letter proposes a deterministic coded network that leverages wireless diversity for semi-decentralized FL without requiring prior information about the entire network. Furthermore, the theoretical analyses of the outage and the convergence rate of the proposed scheme are provided. Finally, the superiority of our proposed method over benchmark methods is demonstrated through comprehensive simulations.

In this paper, we investigate the problem of distributed learning (DL) in the presence of Byzantine attacks. For this problem, various robust bounded aggregation (RBA) rules have been proposed at the central server to mitigate the impact of Byzantine attacks. However, current DL methods apply RBA rules for the local gradients from the honest devices and the disruptive information from Byzantine devices, and the learning performance degrades significantly when the local gradients of different devices vary considerably from each other. To overcome this limitation, we propose a new DL method to cope with Byzantine attacks based on coded robust aggregation (CRA-DL). Before training begins, the training data are allocated to the devices redundantly. During training, in each iteration, the honest devices transmit coded gradients to the server computed from the allocated training data, and the server then aggregates the information received from both honest and Byzantine devices using RBA rules. In this way, the global gradient can be approximately recovered at the server to update the global model. Compared with current DL methods applying RBA rules, the improvement of CRA-DL is attributed to the fact that the coded gradients sent by the honest devices are closer to each other. This closeness enhances the robustness of the aggregation against Byzantine attacks, since Byzantine messages tend to be significantly different from those of honest devices in this case. We theoretically analyze the convergence performance of CRA-DL. Finally, we present numerical results to verify the superiority of the proposed method over existing baselines, showing its enhanced learning performance under Byzantine attacks.

In this paper, we consider the problem of federated learning (FL) with devices that have intermittent connectivity to the central server. For this problem, the concept of semi-decentralized FL has been proposed in the literature. This paradigm allows non-straggler devices to relay the gradients computed by the stragglers to the server, and enables realization of gradient coding (GC) to mitigate the negative impact of the stragglers that fail to communicate directly to the central server. However, for GC in semi-decentralized FL, the communication overhead caused by information transmission among the devices is significant. To overcome this shortcoming, inspired by the existing communication-optimal exact consensus algorithm (CECA), we propose a new communication-efficient semi-decentralized FL method (COFFEE). In each round, the devices exchange information by taking a certain number of steps towards communication-optimal exact consensus, ensuring that each device obtains the average of the gradients computed by both its previous neighbors and itself. Afterwards, the non-stragglers transmit the local average result to the server for global aggregation to update the global model. We analyze the convergence performance and the communication overhead of COFFEE analytically. Building on this, to further enhance learning performance under a specific communication overhead, we propose an enhanced version of COFFEE with an adaptive aggregation rule at the central server, referred to as A-COFFEE, which adjusts to the straggler pattern of the devices over training rounds. Experiments are conducted to verify that the proposed methods outperform the baseline methods.

This work studies gradient coding (GC) in the context of distributed training problems with unreliable communication. We propose cooperative GC (CoGC), a novel gradient-sharing-based GC framework that leverages cooperative communication among clients. This approach eliminates the need for dataset replication, making it communication- and computation-efficient and suitable for federated learning (FL). By employing the standard GC decoding mechanism, CoGC yields strictly binary outcomes: the global model is either recovered exactly or the recovery is meaningless, with no intermediate outcomes. This characteristic ensures the optimality of the training and demonstrates strong resilience to client-to-server communication failures. However, due to the limited flexibility of the recovery outcomes, the decoding mechanism may also result in communication inefficiency and hinder convergence, especially when communication channels among clients are in poor condition. To overcome this limitation and further exploit the potential of GC matrices, we propose a complementary decoding mechanism, termed GC⁺, which leverages information that would otherwise be discarded during GC decoding failures. This approach significantly improves system reliability against unreliable communication, as the full recovery¹ of the global model dominates in GC⁺. To conclude, this work establishes solid theoretical frameworks for both CoGC and GC⁺. We assess the system reliability by outage analyses and convergence analyses for each decoding mechanism, along with a rigorous investigation of how outages affect the structure and performance of GC matrices. Finally, the effectiveness of CoGC and GC⁺ is validated through extensive simulations.