Accurate channel state information (CSI) is fundamental to reliable and efficient wireless communication. However, traditional pilot-based channel estimation introduces considerable overhead, particularly in massive multiple-input multiple-output (MIMO) systems. This paper investigates pilot-free channel inference to estimate complete CSI directly from multimodal sensing observations, including camera images, LiDAR point clouds, and GPS coordinates. Specifically, we propose a multimodal flow matching framework that fuses heterogeneous sensing modalities into a latent distribution in the channel space, and learns a velocity field that continuously transports samples from the source latent distribution toward the target channel distribution. To shorten and straighten the transport trajectory, we introduce a modality alignment loss that not only regularizes the encoded source distribution but also encourages it to align with the target channel distribution. During inference, the learned flow is efficiently approximated using a second-order numerical integrator. For evaluation, we construct a multimodal simulation dataset with Sionna and Blender, enabling realistic modeling of sensing scenes and wireless propagation. System-level experiments demonstrate that the proposed approach outperforms both pilot-based and sensing-aided baselines in channel estimation accuracy under dynamic environments.

To support real-world decision-making, it is crucial for models to be well-calibrated, i.e., to assign reliable confidence estimates to their predictions. Uncertainty quantification is particularly important in personalized federated learning (PFL), as participating clients typically have small local datasets, making it difficult to unambiguously determine optimal model parameters. Bayesian PFL (BPFL) methods can potentially enhance calibration, but they often come with considerable computational and memory requirements due to the need to track the variances of all the individual model parameters. Furthermore, different clients may exhibit heterogeneous uncertainty levels owing to varying local dataset sizes and distributions. To address these challenges, we propose LR-BPFL, a novel BPFL method that learns a global deterministic model along with personalized low-rank Bayesian corrections. To tailor the local model to each client’s inherent uncertainty level, LR-BPFL incorporates an adaptive rank selection mechanism. We evaluate LR-BPFL across a variety of datasets, demonstrating its advantages in terms of calibration, accuracy, as well as computational and memory requirements. The code is available at \url{https://github.com/Bernie0115/LR-BPFL.}

Federated edge learning(FEEL) is a popular distributed learning framework for privacy-preserving at the edge, in which densely distributed edge devices periodically exchange model-updates with the server to complete the global model training. Due to limited bandwidth and uncertain wireless environment, FEEL may impose heavy burden to the current communication system. In addition, under the common FEEL framework, the server needs to wait for the slowest device to complete the update uploading before starting the aggregation process, leading to the straggler issue that causes prolonged communication time. In this paper, we propose to accelerate FEEL from two aspects: i.e., 1) performing data compression on the edge devices and 2) setting a deadline on the edge server to exclude the straggler devices. However, undesired gradient compression errors and transmission outage are introduced by the aforementioned operations respectively, affecting the convergence of FEEL as well. In view of these practical issues, we formulate a training time minimization problem, with the compression ratio and deadline to be optimized. To this end, an asymptotically unbiased aggregation scheme is first proposed to ensure zero optimality gap after convergence, and the impact of compression error and transmission outage on the overall training time are quantified through convergence analysis. Then, the formulated problem is solved in an alternating manner, based on which, the noveljoint compression and deadline optimization(JCDO) algorithm is derived. Numerical experiments for different use cases in FEEL including image classification and autonomous driving show that the proposed method is nearly 30X faster than the vanilla FedSGD algorithm, and outperforms the state-of-the-art schemes.

The recent development of scalable Bayesian inference methods has renewed interest in the adoption of Bayesian learning as an alternative to conventional frequentist learning that offers improved model calibration via uncertainty quantification. Recently, federated averaging Langevin dynamics (FALD) was introduced as a variant of federated averaging that can efficiently implement distributed Bayesian learning in the presence of noiseless communications. In this paper, we propose wireless FALD (WFALD), a novel protocol that realizes FALD in wireless systems by integrating over-the-air computation and channel-driven sampling for Monte Carlo updates. Unlike prior work on wireless Bayesian learning, WFALD enables (i) multiple local updates between communication rounds; and (ii) stochastic gradients computed by mini-batch. A convergence analysis is presented in terms of the 2- Wasserstein distance between the samples produced by WFALD and the targeted global posterior distribution. Analysis and experiments show that, when the signal-to-noise ratio is sufficiently large, channel noise can be fully repurposed for Monte Carlo sampling, thus entailing no loss in performance.

Most works on federated learning (FL) focus on the most common frequentist formulation of learning whereby the goal is minimizing the global empirical loss. Frequentist learning, however, is known to be problematic in the regime of limited data as it fails to quantify epistemic uncertainty in prediction. Bayesian learning provides a principled solution to this problem by shifting the optimization domain to the space of distribution in the model parameters. This paper proposes a novel mechanism for the efficient implementation of Bayesian learning in wireless systems. Specifically, we focus on a standard gradient-based Markov Chain Monte Carlo (MCMC) method, namely Langevin Monte Carlo (LMC), and we introduce a novel protocol, termed Wireless Federated LMC (WFLMC), that is able to repurpose channel noise for the double role of seed randomness for MCMC sampling and of privacy preservation. To this end, based on the analysis of the Wasserstein distance between sample distribution and global posterior distribution under privacy and power constraints, we introduce a power allocation strategy as the solution of a convex program. The analysis identifies distinct operating regimes in which the performance of the system is power-limited, privacy-limited, or limited by the requirement of MCMC sampling. Both analytical and simulation results demonstrate that, if the channel noise is properly accounted for under suitable conditions, it can be fully repurposed for both MCMC sampling and privacy preservation, obtaining the same performance as in an ideal communication setting that is not subject to privacy constraints.

Conventional frequentist learning, as assumed by existing federated learning protocols, is limited in its ability to quantify uncertainty, incorporate prior knowledge, guide active learning, and enable continual learning. Bayesian learning provides a principled approach to address all these limitations, at the cost of an increase in computational complexity. This paper studies distributed Bayesian learning in a wireless data center setting encompassing a central server and multiple distributed workers. Prior work on wireless distributed learning has focused exclusively on frequentist learning, and has introduced the idea of leveraging uncoded transmission to enable “over-the-air” computing. Unlike frequentist learning, Bayesian learning aims at evaluating approximations or samples from a global posterior distribution in the model parameter space. This work investigates for the first time the design of distributed one-shot, or “embarrassingly parallel”, Bayesian learning protocols in wireless data centers via consensus Monte Carlo (CMC). Uncoded transmission is introduced not only as a way to implement “over-the-air” computing, but also as a mechanism to deploychannel-driven MC sampling: Rather than treating channel noise as a nuisance to be mitigated, channel-driven sampling utilizes channel noise as an integral part of the MC sampling process. A simple wireless CMC scheme is first proposed that is asymptotically optimal under Gaussian local posteriors. Then, for arbitrary local posteriors, a variational optimization strategy is introduced. Simulation results demonstrate that, if properly accounted for, channel noise can indeed contribute to MC sampling and does not necessarily decrease the accuracy level.

Federated Learning (FL) refers to distributed protocols that avoid direct raw data exchange among the participating devices while training for a common learning task. This way, FL can potentially reduce the information on the local data sets that is leaked via communications. In order to provide formal privacy guarantees, however, it is generally necessary to put in place additional masking mechanisms. When FL is implemented in wireless systems via uncoded transmission, the channel noise can directly act as a privacy-inducing mechanism. This paper demonstrates that, as long as the privacy constraint level, measured via differential privacy (DP), is below a threshold that decreases with the signal-to-noise ratio (SNR), uncoded transmission achieves privacy “for free”, i.e., without affecting the learning performance. More generally, this work studies adaptive power allocation (PA) for distributed gradient descent in wireless FL with the aim of minimizing the learning optimality gap under privacy and power constraints. Both orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) transmission with “over-the-air-computing” are studied, and solutions are obtained in closed form for an offline optimization setting. Furthermore, heuristic online methods are proposed that leverage iterative one-step-ahead optimization. The importance of dynamic PA and the potential benefits of NOMA versus OMA are demonstrated through extensive simulations.

By deploying machine-learning algorithms at the network edge, edge learning can leverage the enormous real-time data generated by billions of mobile devices to train AI models, which enable intelligent mobile applications. In this emerging research area, one key direction is to efficiently utilize radio resources for wireless data acquisition to minimize the latency of executing a learning task at an edge server. Along this direction, we consider the specific problem of retransmission decision in each communication round to ensure both reliability and quantity of those training data for accelerating model convergence. To solve the problem, a new retransmission protocol called data-importance aware automatic-repeat-request (importance ARQ) is proposed. Unlike the classic ARQ focusing merely on reliability, importance ARQ selectively retransmits a data sample based on its uncertainty which helps learning and can be measured using the model under training. Underpinning the proposed protocol is a derived elegant communication-learning relation between two corresponding metrics, i.e., signal-to-noise ratio (SNR) and data uncertainty. This relation facilitates the design of a simple threshold based policy for importance ARQ. The policy is first derived based on the classic classifier model of support vector machine (SVM), where the uncertainty of a data sample is measured by its distance to the decision boundary. The policy is then extended to the more complex model of convolutional neural networks (CNN) where data uncertainty is measured by entropy. Extensive experiments have been conducted for both the SVM and CNN using real datasets with balanced and imbalanced distributions. Experimental results demonstrate that importance ARQ effectively copes with channel fading and noise in wireless data acquisition to achieve faster model convergence than the conventional channel-aware ARQ. The gain is more significant when the dataset is imbalanced.

Multimedia content, especially videos, is expected to dominate data traffic in next-generation mobile networks. Caching popular content at the network edge, namely content helpers (base stations and access points), has emerged as a solution for low-latency content delivery. Compared with traditional wireless communication, content delivery has a key characteristic that many signals coexisting in the air carry identical popular content. However, they can interfere with each other at a receiver if their modulation-and-coding (MAC) schemes are adapted to individual channels following the classic approach. To address this issue, we present a novel idea of content adaptive MAC (CAMAC) where adapting MAC schemes to content ensures that all signals carrying identical content are encoded using an identical MAC scheme to achieve spatial MAC alignment. Consequently, interference can be harnessed as signals to improve the reliability of wireless delivery. In the remaining part of the paper, we focus on quantifying the gain that CAMAC can bring to a content-delivery network by using a stochastic-geometry model. Specifically, content helpers are distributed as a Poisson point process and each of them transmits a file from a content database based on a given popularity distribution. Given a fixed threshold on the signal-to-interference ratio for successful transmission, it is discovered that the successful content-delivery probability is closely related to the distribution of the ratio of two independent shot noise processes, named a shot-noise ratio. The distribution itself is an open mathematical problem that we tackle in this work. Using stable-distribution theory and tools from stochastic geometry, the distribution function is derived in closed form. Extending the result in the context of content-delivery networks with CAMAC yields the content-delivery probability in different closed forms. In addition, the gain in the probability due to CAMAC is shown to grow with the level of skewness in the content popularity distribution.

As multimedia content is becoming increasingly dominant in mobile data traffic, low-latency content delivery will be a key feature for next-generation radio access networks. For wireless content delivery, many signals over the air carry identical popular content. However, they can interfere with each other at a receiver if their modulation-and-coding (MAC) schemes are adapted to individual channels. To cope with this issue, we present a novel idea of content adaptive MAC (CAMAC) to ensure that all signals carry identical content are encoded using an uniform MAC scheme and thus interference can be harnessed as signals, thereby improving the reliability of wireless delivery. In quantify the resultant performance gain, we consider a model of content delivery network where the content helpers are distributed as a Poisson point process and each of them randomly transmits a file based on a given popularity distribution. It is found that the (successful) content-delivery probability depends on the distribution of a shot-noise ratio, referring to the ratio of two independent shot-noise processes. Its distribution is an open mathematical problem that we tackle in this work using stable distribution theory and tools from stochastic geometry. The results allow the derivation of content-delivery probability in different closed forms. Then the gain in the probability due to CAMAC is quantified and shown to grow with the level of skewness in the content popularity distribution.