Federated learning (FL) has been considered as a promising way to train distributed wireless systems in a privacy-preserving manner. However, the significant communications overheads caused by uploading local parameters and the potential unreliability of wireless links emerged as one of the bottlenecks of FL. To address this challenge, this paper investigates a reconfigurable intelligent surface (RIS)-assisted sparse FL network, where the RIS is utilized for wireless transmission reliability enhancement, and the sparsification operation is used to reduce the communications overheads. Considering that the wireless transmissions of the FL uploads are carried by finite blocklength (FBL) codes, wefor the first timeinvestigate the convergence of sparse FL while taking into account both the FBL decoding errors and FL sparsification errors. Following such a model, a novel joint learning and communication design framework is provided. In particular, an optimization problem is formulated to minimize the impacts of the above errors on the convergence via jointly determining the coding rate, transmit power, and RIS phase shift. To tackle the formulated non-convex problem, a block coordinate descent (BCD)-based algorithm is proposed, which decomposes the problem into two sub-ones and solves them alternately. On the one hand, for the resource allocation sub-problem, we derive a closed-form expression of optimal coding rate with respect to power that drastically reduces the optimization problem dimension, and shows the convexity of the resulting power allocation problem. For the RIS phase shift design sub-problem, on the other hand, a trust-region based linear approximation is used, along with problem transformations and tight successive convex approximations, to derive a highly effective iterative algorithm based on the closed-form expression for each variable. The entire proposed iterative algorithm converges efficiently to a suboptimal solution. Then, we extend the proposed algorithm to the imperfect channel state information (CSI) scenarios by using second-order Taylor approximation. Numerical results demonstrate that the proposed design significantly improves the FL performance in comparison to benchmark schemes.

Distributed edge learning (DL) is considered a cornerstone of intelligence enablers, since it allows for collaborative training without the necessity for local clients to share raw data with other parties, thereby preserving privacy and security. Integrating DL into the 6G networks requires a coexistence design with existing services such as high-bandwidth (HB) traffic like eMBB. Current designs in the literature mainly focus on communication round-wise designs that assume a rigid resource allocation throughout each communication round (CR). However, rigid resource allocation within a CR is a highly inefficient and inaccurate representation of the system’s realistic behavior, especially when CR duration far exceeds the channel coherence time due to large model size or limited resources. This is due to the heterogeneous nature of the system, as clients inherently may need to access the network at different time instants. This work zooms into one arbitrary CR, and demonstrates the importance of considering a time-dependent design for sharing the resource pool with HB traffic. We first formulate a time-slot-wise optimization problem to minimize the consumed time by DL within the CR while constrained by a DL energy budget. Due to its intractability, a session-based optimization problem is formulated assuming a CR lasts less than a large-scale coherence time. Some scheduling properties of such multi-server joint communication scheduling and resource allocation framework have been established. An iterative algorithm has been designed to solve such non-convex and non-block-separable-constrained problems. Simulation results confirm the importance of the efficient and accurate integration design proposed in this work.

Distributed learning (DL) is considered a cornerstone of intelligence enabler, since it allows for collaborative training without the necessity for local clients to share raw data with other parties, thereby preserving privacy and security. Integrating DL into the 6G networks requires coexistence design with existing services such as high-bandwidth (HB) traffic like eMBB. Current designs in the literature mainly focus on communication round (CR)-wise designs that assume a fixed resource allocation during each CR. However, fixed resource allocation within a CR is a highly inefficient and inaccurate representation of the system's realistic behavior. This is due to the heterogeneous nature of the system, where clients inherently need to access the network at different times. This work zooms into one arbitrary communication round and demonstrates the importance of considering a time-dependent resource-sharing design with HB traffic. We propose a time-dependent optimization problem for minimizing the consumed time and energy by DL within the CR. Due to its intractability, a session-based optimization problem has been proposed assuming a large-scale coherence time. An iterative algorithm has been designed to solve such problems and simulation results confirm the importance of such efficient and accurate integration design.

We consider a reconfigurable intelligent surface (RIS)-aided wireless network supporting local gradient upload for federated learning (FL). For the first time, the impact of wireless uploads with finite blocklength (FBL) on FL performance is investigated and provides a corresponding performance enhancement design. More specifically, we characterize the im-pact of wireless transmissions/uploads on the convergence and the optimality gap of FL, and formulate a resource allocation problem to minimize such impact accordingly. To tackle the formulated non-convex problem, we first conduct a convex approximation to the problem, then propose a block coordinate descent (BCD) based algorithm alternately optimizing the power allocation and RIS phase shifts via addressing two sub-problems. Specifically, we prove the convexity for the pure power allocation sub-problem, while for RIS phase design one, a closed-form expression of the optimal solution is derived by applying the path-following (PF) method. Numerical results demonstrate that the proposed design significantly improves the FL performance compared to baseline schemes.

The strict block error rate (BLER) requirement under the time-varying nature of wireless channels in Ultra-reliable low-latency communication (URLLC) systems pose sig-nificant challenges for link adaptation (LA). To tackle these challenges, we propose a novel LA method that adaptively selects the modulation and coding scheme (MCS) without requiring perfect channel knowledge which is unrealistic to obtain in URLLC. The goal is to maximize the coding rate while ensuring strict BLER constraints in URLLC systems. To achieve this, we utilize the Deep Q-Network (DQN) algorithm to select the MCS dynamically. Furthermore, we enhance the MCS selection process by using the Outer Loop Link Adaptation algorithm for transmission reliability improvement. Given the nature of URLLC, the samples of ACK and NACK are highly imbalanced, which can cause issues in the training process. To address it, we propose a novel training mechanism that improves the performance of DQN model and convergence speed during the training stage. Through extensive simulations, we demonstrate that our proposed algorithm outperforms existing methods regarding coding rate and imposing strict BLER constraints.

In federated learning (FL), local workers learn a global model collaboratively using their local data by communicating trained models to a central server for privacy concerns. Due to its local nature, FL is typically subject to various heterogeneities, including system and statistical heterogeneity. To address these concerns, Federated Proximal (FedProx) has been considered a promising FL paradigm to provide more stable learning convergence in the presence of computation stragglers and statistical heterogeneity. However, in wireless networks with unreliable communication channels, the errors of packet transmissions should be considered, introducing additional heterogeneity. For the first time, we rigorously prove the convergence of FedProx in the presence of transmission packet errors in heterogeneous networks. In addition, we propose a joint client selection and resource allocation strategy that maximizes the number of effective participating users for convergence acceleration. The method is combined with a random weight mechanism to reduce the statistical bias caused by the client selection strategy. An efficient low-complexity algorithm for solving the optimization problem is developed. The proposed method achieves faster convergence and requires fewer communication rounds to attain accuracy than existing state-of-the-art client selection methods.

Denoising, detrending, deconvolution: usual restoration tasks, traditionally decoupled. Coupled formulations entail complex ill-posed inverse problems. We propose PENDANTSS for joint trend removal and blind deconvolution of sparse peak-like signals. It blends a parsimonious prior with the hypothesis that smooth trend and noise can somewhat be separated by low-pass filtering. We combine the generalized quasi-norm ratio SOOT/SPOQ sparse penalties $\ell_p/\ell_q$ with the BEADS ternary assisted source separation algorithm. This results in a both convergent and efficient tool, with a novel Trust-Region block alternating variable metric forward-backward approach. It outperforms comparable methods, when applied to typically peaked analytical chemistry signals. Reproducible code is provided.

Mobile edge computing (MEC) based heterogeneous vehicular networks (HetVNets) can interwork between IEEE 802.11p-based vehicular networks and cellular-assisted vehicular networks for vehicle-to-everything (V2X) communications. It is an attractive technology for supporting low latency applications for vehicles. However, in the practical system without precise prior knowledge of the dynamic wireless environment, solving joint vehicle-to-edge (V2E) association and resource allocation problem is a challenge. In this paper, first, we use stochastic geometry to model a real scenario. Specifically, the intersection area is modeled as two perpendicular streets, the spatial distribution of vehicle nodes on each street is modeled as an independent one-dimensional (1D) homogeneous Poisson Point Process (PPP), the spatial distribution of different types of edge nodes is modeled as different and independent PPPs. We consider the service time during which a vehicle node with different types of network interfaces gets a service from an edge node. Then, a deep reinforcement learning (DRL) based method is proposed to solve the uplink-and-downlink V2E association problem minimizing the service time while ensuring the computation resource allocation constraints. Simulation results illustrate the better performance of our solution than that of other traditional methods.

This work is related to ultra-reliable and low latency communication (URLLC) in Internet-of-Thing (IoT) networks. In particular, we consider a multi-device IoT network performing blind retransmissions on shared radio resources. We characterize the reliability and goodput performances of such network in the finite blocklength regime. In addition, following the characterization we provide two designs minimizing the error probability and maximizing the network goodput (under reliability constraints), respectively. In particular, the optimal solution is obtained for the reliability-oriented design. In addition, an efficient solution is proposed for the second design maximizing the goodput, which provides a performance tightly close to the one obtained via exhaustive search. Through simulation, we validate our analytical model and evaluate the system performance.