Decentralized Federated Learning by Partial Message Exchange

Decentralized federated learning (DFL) has emerged as a transformative server-free paradigm that enables collaborative learning over large-scale heterogeneous networks. However, it continues to face fundamental challenges, including data heterogeneity, restrictive assumptions for theoretical analysis, and degraded convergence when standard communication- or privacyenhancing techniques are applied. To overcome these drawbacks, this paper develops a novel algorithm, PaME (DFL by Partial Message Exchange). The central principle is to allow only randomly selected sparse coordinates to be exchanged between two neighbor nodes. Consequently, PaME achieves substantial reductions in communication costs while still preserving a high level of privacy, without sacrificing accuracy. Moreover, grounded in rigorous analysis, the algorithm is shown to converge at a linear rate under the gradient to be locally Lipschitz continuous and the communication matrix to be doubly stochastic. These two mild assumptions not only dispense with many restrictive conditions commonly imposed by existing DFL methods but also enables PaME to effectively address data heterogeneity. Furthermore, comprehensive numerical experiments demonstrate its superior performance compared with several representative decentralized learning algorithms.

Event-Triggered Gossip for Distributed Learning

While distributed learning offers a new learning paradigm for distributed network with no central coordination, it is constrained by communication bottleneck between nodes. We develop a new event-triggered gossip framework for distributed learning to reduce inter-node communication overhead. The framework introduces an adaptive communication control mechanism that enables each node to autonomously decide in a fully decentralized fashion when to exchange model information with its neighbors based on local model deviations. We analyze the ergodic convergence of the proposed framework under noconvex objectives and interpret the convergence guarantees under different triggering conditions. Simulation results show that the proposed framework achieves substantially lower communication overhead than the state-of-the-art distributed learning methods, reducing cumulative point-to-point transmissions by \textbf{71.61\%} with only a marginal performance loss, compared with the conventional full-communication baseline.

Robust Processing and Learning: Principles, Methods, and Wireless Applications

This tutorial-style overview article examines the fundamental principles and methods of robustness, using wireless sensing and communication (WSC) as the narrative and exemplifying framework. First, we formalize the conceptual and mathematical foundations of robustness, highlighting the interpretations and relations across robust statistics, optimization, and machine learning. Key techniques, such as robust estimation and testing, distributionally robust optimization, and regularized and adversary training, are investigated. Together, the costs of robustness in system design, for example, the compromised nominal performances and the extra computational burdens, are discussed. Second, we review recent robust signal processing solutions for WSC that address model mismatch, data scarcity, adversarial perturbation, and distributional shift. Specific applications include robust ranging-based localization, modality sensing, channel estimation, receive combining, waveform design, and federated learning. Through this effort, we aim to introduce the classical developments and recent advances in robustness theory to the general signal processing community, exemplifying how robust statistical, optimization, and machine learning approaches can address the uncertainties inherent in WSC systems.

A New Particle Filter for Target Tracking in MIMO OFDM Integrated Sensing and Communications

Particle filtering for target tracking using multi-input multi-output (MIMO) pulse-Doppler radars faces three long-standing obstacles: a) the absence of reliable likelihood models for raw radar data; b) the computational and statistical complications that arise when nuisance parameters (e.g., complex path gains) are augmented into state vectors; and c) the prohibitive computational burden of extracting noisy measurements of range, Doppler, and angles from snapshots. Motivated by an optimization-centric interpretation of Bayes' rule, this article addresses these challenges by proposing a new particle filtering framework that evaluates each hypothesized state using a tailored cost function, rather than relying on an explicit likelihood relation. The framework yields substantial reductions in both running time and tracking error compared to existing schemes. In addition, we examine the implementation of the proposed particle filter in MIMO orthogonal frequency-division multiplexing (OFDM) systems, aiming to equip modern communication infrastructure with integrated sensing and communications (ISAC) capabilities. Experiments suggest that MIMO-OFDM with pulse-Doppler processing holds considerable promise for ISAC, particularly when wide bandwidth, extended on-target time, and large antenna aperture are utilized.

Neural Collapse based Deep Supervised Federated Learning for Signal Detection in OFDM Systems

Future wireless networks are expected to be AI-empowered, making their performance highly dependent on the quality of training datasets. However, physical-layer entities often observe only partial wireless environments characterized by different power delay profiles. Federated learning is capable of addressing this limited observability, but often struggles with data heterogeneity. To tackle this challenge, we propose a neural collapse (NC) inspired deep supervised federated learning (NCDSFL) algorithm.

SpikACom: A Neuromorphic Computing Framework for Green Communications

The ever-growing power consumption of wireless communication systems necessitates more energy-efficient algorithms. This paper introduces SpikACom ({Spik}ing {A}daptive {Com}munication), a neuromorphic computing-based framework for power-intensive wireless communication tasks. SpikACom leverages brain-inspired spiking neural networks (SNNs) for efficient signal processing. It is designed for dynamic wireless environments, helping to mitigate catastrophic forgetting and facilitate adaptation to new circumstances. Moreover, SpikACom is customizable, allowing flexibly integration of domain knowledge to enhance it interpretability and efficacy. We validate its performance on fundamental wireless communication tasks, including task-oriented semantic communication, multiple-input multiple-output (MIMO) beamforming, and orthogonal frequency-division multiplexing (OFDM) channel estimation. The simulation results show that SpikACom significantly reduces power consumption while matching or exceeding the performance of conventional algorithms. This study highlights the potential of SNNs for enabling greener and smarter wireless communication systems.

Task-Oriented Semantic Communication for Stereo-Vision 3D Object Detection

With the development of computer vision, 3D object detection has become increasingly important in many real-world applications. Limited by the computing power of sensor-side hardware, the detection task is sometimes deployed on remote computing devices or the cloud to execute complex algorithms, which brings massive data transmission overhead. In response, this paper proposes an optical flow-driven semantic communication framework for the stereo-vision 3D object detection task. The proposed framework fully exploits the dependence of stereo-vision 3D detection on semantic information in images and prioritizes the transmission of this semantic information to reduce total transmission data sizes while ensuring the detection accuracy. Specifically, we develop an optical flow-driven module to jointly extract and recover semantics from the left and right images to reduce the loss of the left-right photometric alignment semantic information and improve the accuracy of depth inference. Then, we design a 2D semantic extraction module to identify and extract semantic meaning around the objects to enhance the transmission of semantic information in the key areas. Finally, a fusion network is used to fuse the recovered semantics, and reconstruct the stereo-vision images for 3D detection. Simulation results show that the proposed method improves the detection accuracy by nearly 70% and outperforms the traditional method, especially for the low signal-to-noise ratio regime.

Low-Complexity Multi-Target Detection in ELAA ISAC

Multi-target detection and communication with extremely large-scale antenna arrays (ELAAs) operating at high frequencies necessitate generating multiple beams. However, conventional algorithms are slow and computationally intensive. For instance, they can simulate a \num{200}-antenna system over two weeks, and the time complexity grows exponentially with the number of antennas. Thus, this letter explores an ultra-low-complex solution for a multi-user, multi-target integrated sensing and communication (ISAC) system equipped with an ELAA base station (BS). It maximizes the communication sum rate while meeting sensing beampattern gain targets and transmit power constraints. As this problem is non-convex, a Riemannian stochastic gradient descent-based augmented Lagrangian manifold optimization (SGALM) algorithm is developed, which searches on a manifold to ensure constraint compliance. The algorithm achieves ultra-low complexity and superior runtime performance compared to conventional algorithms. For example, it is \num{56} times faster than the standard benchmark for \num{257} BS antennas.

Beam Structured Turbo Receiver for HF Skywave Massive MIMO

In this paper, we investigate receiver design for high frequency (HF) skywave massive multiple-input multiple-output (MIMO) communications. We first establish a modified beam based channel model (BBCM) by performing uniform sampling for directional cosine with deterministic sampling interval, where the beam matrix is constructed using a phase-shifted discrete Fourier transform (DFT) matrix. Based on the modified BBCM, we propose a beam structured turbo receiver (BSTR) involving low-dimensional beam domain signal detection for grouped user terminals (UTs), which is proved to be asymptotically optimal in terms of minimizing mean-squared error (MSE). Moreover, we extend it to windowed BSTR by introducing a windowing approach for interference suppression and complexity reduction, and propose a well-designed energy-focusing window. We also present an efficient implementation of the windowed BSTR by exploiting the structure properties of the beam matrix and the beam domain channel sparsity. Simulation results validate the superior performance of the proposed receivers but with remarkably low complexity.

Large Model Empowered Streaming Semantic Communications for Speech Translation

Semantic communications have been explored to perform downstream intelligent tasks by extracting and transmitting essential information. In this paper, we introduce a large model-empowered streaming semantic communication system for speech translation across various languages, named LaSC-ST. Specifically, we devise an edge-device collaborative semantic communication architecture by offloading the intricate semantic extraction module to edge servers, thereby reducing the computational burden on local devices. To support multilingual speech translation, pre-trained large speech models are utilized to learn unified semantic features from speech in different languages, breaking the constraint of a single input language and enhancing the practicality of the LaSC-ST. Moreover, the input speech is sequentially streamed into the developed system as short speech segments, which enables low transmission latency without the degradation in speech translation quality. A novel dynamic speech segmentation algorithm is proposed to further minimize the transmission latency by adaptively adjusting the duration of speech segments. According to simulation results, the LaSC-ST provides more accurate speech translation and achieves streaming transmission with lower latency compared to existing non-streaming semantic communication systems.