arXiv subjects

Mehdi Bennis

Publications and source records attributed to Mehdi Bennis.

At least 73 records · Page 4Linked to original sources

arXiv2025

Large-Scale AI in Telecom: Charting the Roadmap for Innovation, Scalability, and Enhanced Digital Experiences

This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems. It highlights the development and deployment of Large Telecom Models (LTMs), which are tailored AI models designed to address the complex challenges faced by modern telecom networks. The paper covers a wide range of topics, from the architecture and deployment strategies of LTMs to their applications in network management, resource allocation, and optimization. It also explores the regulatory, ethical, and standardization considerations for LTMs, offering insights into their future integration into telecom infrastructure. The goal is to provide a comprehensive roadmap for the adoption of LTMs to enhance scalability, performance, and user-centric innovation in telecom networks.

cs.NI↗

arXiv2025

Sequence Spreading-Based Semantic Communication Under High RF Interference

In the evolving landscape of wireless communications, semantic communication (SemCom) has recently emerged as a 6G enabler that prioritizes the transmission of meaning and contextual relevance over conventional bit-centric metrics. However, the deployment of SemCom systems in industrial settings presents considerable challenges, such as high radio frequency interference (RFI), that can adversely affect system performance. To address this problem, in this work, we propose a novel approach based on integrating sequence spreading techniques with SemCom to enhance system robustness against such adverse conditions and enable scalable multi-user (MU) SemCom. In addition, we propose a novel signal refining network (SRN) to refine the received signal after despreading and equalization. The proposed network eliminates the need for computationally intensive end-to-end (E2E) training while improving performance metrics, achieving a 25% gain in BLEU score and a 12% increase in semantic similarity compared to E2E training using the same bandwidth.

cs.NI↗

arXiv2025

Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning

In this article, we propose a communication-efficient decentralized machine learning (ML) algorithm, coined quantized group ADMM (Q-GADMM). To reduce the number of communication links, every worker in Q-GADMM communicates only with two neighbors, while updating its model via the group alternating direction method of multipliers (GADMM). Moreover, each worker transmits the quantized difference between its current model and its previously quantized model, thereby decreasing the communication payload size. However, due to the lack of centralized entity in decentralized ML, the spatial sparsity and payload compression may incur error propagation, hindering model training convergence. To overcome this, we develop a novel stochastic quantization method to adaptively adjust model quantization levels and their probabilities, while proving the convergence of Q-GADMM for convex objective functions. Furthermore, to demonstrate the feasibility of Q-GADMM for non-convex and stochastic problems, we propose quantized stochastic GADMM (Q-SGADMM) that incorporates deep neural network architectures and stochastic sampling. Simulation results corroborate that Q-GADMM significantly outperforms GADMM in terms of communication efficiency while achieving the same accuracy and convergence speed for a linear regression task. Similarly, for an image classification task using DNN, Q-SGADMM achieves significantly less total communication cost with identical accuracy and convergence speed compared to its counterpart without quantization, i.e., stochastic GADMM (SGADMM).

cs.LG↗

arXiv2025

Scalable and Resource-Efficient Second-Order Federated Learning via Over-the-Air Aggregation

Second-order federated learning (FL) algorithms offer faster convergence than their first-order counterparts by leveraging curvature information. However, they are hindered by high computational and storage costs, particularly for large-scale models. Furthermore, the communication overhead associated with large models and digital transmission exacerbates these challenges, causing communication bottlenecks. In this work, we propose a scalable second-order FL algorithm using a sparse Hessian estimate and leveraging over-the-air aggregation, making it feasible for larger models. Our simulation results demonstrate more than $67\%$ of communication resources and energy savings compared to other first and second-order baselines.

cs.LG↗

arXiv2025

Intent-Aware DRL-Based NOMA Uplink Dynamic Scheduler for IIoT

We investigate the problem of supporting Industrial Internet of Things user equipment (IIoT UEs) with intent (i.e., requested quality of service (QoS)) and random traffic arrival. A deep reinforcement learning (DRL) based centralized dynamic scheduler for time-frequency resources is proposed to learn how to schedule the available communication resources among the IIoT UEs. The proposed scheduler leverages an RL framework to adapt to the dynamic changes in the wireless communication system and traffic arrivals. Moreover, a graph-based reduction scheme is proposed to reduce the state and action space of the RL framework to allow fast convergence and a better learning strategy. Simulation results demonstrate the effectiveness of the proposed intelligent scheduler in guaranteeing the expressed intent of IIoT UEs compared to several traditional scheduling schemes, such as round-robin, semi-static, and heuristic approaches. The proposed scheduler also outperforms the contention-free and contention-based schemes in maximizing the number of successfully computed tasks.

cs.IT↗

arXiv2024

The Rendezvous Between Extreme Value Theory and Next-generation Networks

Promising technologies such as massive multiple-input and multiple-output, reconfigurable intelligent reflecting surfaces, non-terrestrial networks, millimetre wave communication, ultra-reliable lowlatency communication are envisioned as the enablers for next-generation (NG) networks. In contrast to conventional communication systems meeting specific average performance requirements, NG systems are expected to meet quality-of-service requirements in extreme scenarios as well. In this regard, extreme value theory (EVT) provides a powerful framework for the design of communication systems. In this paper, we provide a comprehensive survey of advances in communication that utilize EVT to characterize the extreme order statistics of interest. We first give an overview of the history of EVT and then elaborate on the fundamental theorems. Subsequently, we discuss different problems of interest in NG communication systems and how EVT can be utilized for their analysis. We finally point out the open challenges and future directions of EVT in NG communication systems.

cs.IT↗

arXiv2024

Zero-Shot Generalization for Blockage Localization in mmWave Communication

This paper introduces a novel method for predicting blockages in millimeter-wave (mmWave) communication systems towards enabling reliable connectivity. It employs a self-supervised learning approach to label radio frequency (RF) data with the locations of blockage-causing objects extracted from light detection and ranging (LiDAR) data, which is then used to train a deep learning model that predicts object`s location only using RF data. Then, the predicted location is utilized to predict blockages, enabling adaptability without retraining when transmitter-receiver positions change. Evaluations demonstrate up to 74% accuracy in predicting blockage locations in dynamic environments, showcasing the robustness of the proposed solution.

eess.SP↗

arXiv2024

From Raw Data to Structural Semantics: Trade-offs among Distortion, Rate, and Inference Accuracy

This work explores the advantages of using persistence diagrams (PDs), topological signatures of raw point cloud data, in a point-to-point communication setting. PD is a structural semantics in the sense that it carries information about the shape and structure of the data. Instead of transmitting raw data, the transmitter communicates its PD semantics, and the receiver carries out inference using the received semantics. We propose novel qualitative definitions for distortion and rate of PD semantics while quantitatively characterizing the trade-offs among the distortion, rate, and inference accuracy. Simulations demonstrate that unlike raw data or autoencoder (AE)-based latent representations, PD semantics leads to more effective use of transmission channels, enhanced degrees of freedom for incorporating error detection/correction capabilities, and improved robustness to channel imperfections. For instance, in a binary symmetric channel with nonzero crossover probability settings, the minimum rate required for Bose, Chaudhuri, and Hocquenghem (BCH)-coded PD semantics to achieve an inference accuracy over 80% is approximately 15 times lower than the rate required for the coded AE-latent representations. Moreover, results suggest that the gains of PD semantics are even more pronounced when compared with the rate requirements of raw data.

cs.IT↗

arXiv2024

Stacked Intelligent Metasurfaces for Task-Oriented Semantic Communications

Semantic communication (SemCom) leveraging advanced deep learning (DL) technologies enhances the efficiency and reliability of information transmission. Emerging stacked intelligent metasurface (SIM) with an electromagnetic neural network (EMNN) architecture enables complex computations at the speed of light. In this letter, we introduce an innovative SIM-aided SemCom system for image recognition tasks, where a SIM is positioned in front of the transmitting antenna. In contrast to conventional communication systems that transmit modulated signals carrying the image information or compressed semantic information, the carrier EM wave is directly transmitted from the source. The input layer of the SIM performs source encoding, while the remaining multi-layer architecture constitutes an EMNN for semantic encoding, transforming signals into a unique beam towards a receiving antenna corresponding to the image class. Remarkably, both the source and semantic encoding occur naturally as the EM waves propagate through the SIM. At the receiver, the image is recognized by probing the received signal magnitude across the receiving array. To this end, we utilize an efficient mini-batch gradient descent algorithm to train the transmission coefficients of SIM's meta-atoms to learn the semantic representation of the image. Extensive numerical results verify the effectiveness of utilizing the SIM-based EMNN for image recognition task-oriented SemComs, achieving more than 90\% recognition accuracy.

cs.IT↗

arXiv2024

Five Key Enablers for Communication during and after Disasters

Civilian communication during disasters such as earthquakes, floods, and military conflicts is crucial for saving lives. Nevertheless, several challenges exist during these circumstances such as the destruction of cellular communication and electricity infrastructure, lack of line of sight (LoS), and difficulty of localization under the rubble. In this article, we discuss key enablers that can boost communication during disasters, namely, satellite and aerial platforms, redundancy, silencing, and sustainable networks aided with wireless energy transfer (WET). The article also highlights how these solutions can be implemented in order to solve the failure of communication during disasters. Finally, it sheds light on unresolved challenges, as well as future research directions.

eess.SP↗

arXiv2024

MIRA: A Method of Federated MultI-Task Learning for LaRge LAnguage Models

In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that considers other clients' tasks and data distribution. To mitigate the extensive computational and communication overhead often associated with LLMs, we utilize a parameter-efficient fine-tuning method, specifically Low-Rank Adaptation (LoRA), reducing the number of trainable parameters. Experimental results, with different datasets and models, demonstrate the proposed method's effectiveness compared to existing frameworks for federated fine-tuning of LLMs in terms of average and local performances. The proposed scheme outperforms existing baselines by achieving lower local loss for each client while maintaining comparable global performance.

cs.LG↗

arXiv2024

Terahertz-Band Integrated Sensing and Communications: Challenges and Opportunities

The sixth generation (6G) wireless networks aim to achieve ultra-high data transmission rates, very low latency and enhanced energy-efficiency. To this end, terahertz (THz) band is one of the key enablers of 6G to meet such requirements. The THz-band systems are also quickly emerging as high-resolution sensing devices because of their ultra-wide bandwidth and very narrow beamwidth. As a means to efficiently utilize spectrum and thereby save cost and power, THz integrated sensing and communications (ISAC) paradigm envisages a single integrated hardware platform with a common signaling mechanism. However, ISAC at THz-band entails several design challenges such as beam split, range-dependent bandwidth, near-field beamforming, and distinct channel model. This article examines the technologies that have the potential to bring forth ISAC and THz transmission together. In particular, it provides an overview of antenna and array design, hybrid beamforming, integration with reflecting surfaces and data-driven techniques such as machine learning. These systems also provide research opportunities in developing novel methodologies for channel estimation, near-field beam split, waveform design, and beam misalignment.

eess.SP↗

arXiv2024

Cross Layer Optimization and Distributed Reinforcement Learning for Wireless 360° Video Streaming

Wirelessly streaming high quality 360 degree videos is still a challenging problem. When there are many users watching different 360 degree videos and competing for the computing and communication resources, the streaming algorithm at hand should maximize the average quality of experience (QoE) while guaranteeing a minimum rate for each user. In this paper, we propose a cross layer optimization approach that maximizes the available rate to each user and efficiently uses it to maximize users' QoE. Particularly, we consider a tile based 360 degree video streaming, and we optimize a QoE metric that balances the tradeoff between maximizing each user's QoE and ensuring fairness among users. We show that the problem can be decoupled into two interrelated subproblems: (i) a physical layer subproblem whose objective is to find the download rate for each user, and (ii) an application layer subproblem whose objective is to use that rate to find a quality decision per tile such that the user's QoE is maximized. We prove that the physical layer subproblem can be solved optimally with low complexity and an actor-critic deep reinforcement learning (DRL) is proposed to leverage the parallel training of multiple independent agents and solve the application layer subproblem. Extensive experiments reveal the robustness of our scheme and demonstrate its significant performance improvement compared to several baseline algorithms.

cs.LG↗

arXiv2024

Toward Explainable Reasoning in 6G: A Proof of Concept Study on Radio Resource Allocation

The move toward artificial intelligence (AI)-native sixth-generation (6G) networks has put more emphasis on the importance of explainability and trustworthiness in network management operations, especially for mission-critical use-cases. Such desired trust transcends traditional post-hoc explainable AI (XAI) methods to using contextual explanations for guiding the learning process in an in-hoc way. This paper proposes a novel graph reinforcement learning (GRL) framework named TANGO which relies on a symbolic subsystem. It consists of a Bayesian-graph neural network (GNN) Explainer, whose outputs, in terms of edge/node importance and uncertainty, are periodically translated to a logical GRL reward function. This adjustment is accomplished through defined symbolic reasoning rules within a Reasoner. Considering a real-world testbed proof-of-concept (PoC), a gNodeB (gNB) radio resource allocation problem is formulated, which aims to minimize under- and over-provisioning of physical resource blocks (PRBs) while penalizing decisions emanating from the uncertain and less important edge-nodes relations. Our findings reveal that the proposed in-hoc explainability solution significantly expedites convergence compared to standard GRL baseline and other benchmarks in the deep reinforcement learning (DRL) domain. The experiment evaluates performance in AI, complexity, energy consumption, robustness, network, scalability, and explainability metrics. Specifically, the results show that TANGO achieves a noteworthy accuracy of 96.39% in terms of optimal PRB allocation in inference phase, outperforming the baseline by 1.22x.

cs.NI↗

arXiv2024

Learning Latent Wireless Dynamics from Channel State Information

In this work, we propose a novel data-driven machine learning (ML) technique to model and predict the dynamics of the wireless propagation environment in latent space. Leveraging the idea of channel charting, which learns compressed representations of high-dimensional channel state information (CSI), we incorporate a predictive component to capture the dynamics of the wireless system. Hence, we jointly learn a channel encoder that maps the estimated CSI to an appropriate latent space, and a predictor that models the relationships between such representations. Accordingly, our problem boils down to training a joint-embedding predictive architecture (JEPA) that simulates the latent dynamics of a wireless network from CSI. We present numerical evaluations on measured data and show that the proposed JEPA displays a two-fold increase in accuracy over benchmarks, for longer look-ahead prediction tasks.

cs.LG↗

arXiv2024

Deep Learning-Enabled Text Semantic Communication under Interference: An Empirical Study

At the confluence of 6G, deep learning (DL), and natural language processing (NLP), DL-enabled text semantic communication (SemCom) has emerged as a 6G enabler since it minimizes bandwidth consumption, transmission delay, and power usage. Among existing text SemCom techniques, a popular text SemCom scheme -- that can reliably transmit semantic information in the low signal-to-noise ratio (SNR) regimes -- is DeepSC, whose fundamental asymptotic performance limits under radio frequency interference (RFI) were accurately predicted by our recently developed theory [1]. Although our theory was corroborated by simulations, trained deep networks can defy classical statistical wisdom, calling for extensive computer experiments. This empirical work thus follows using the training, validation, and testing sets tokenized and vectorized from the Proceedings of the European Parliament (Europarl) dataset. Specifically, we train the DeepSC architecture in Keras 2.9 with TensorFlow 2.9 as a backend and test it under Gaussian multi-interferer RFI received over Rayleigh fading channels. Our testing results corroborate that DeepSC produces semantically irrelevant sentences under huge Gaussian RFI emitters, validating our theory. Therefore, a fundamental 6G design paradigm for interference-resistant and robust SemCom (IR$^2$ SemCom) is needed.

eess.SP↗

arXiv2024

A Web-Based Solution for Federated Learning with LLM-Based Automation

Federated Learning (FL) offers a promising approach for collaborative machine learning across distributed devices. However, its adoption is hindered by the complexity of building reliable communication architectures and the need for expertise in both machine learning and network programming. This paper presents a comprehensive solution that simplifies the orchestration of FL tasks while integrating intent-based automation. We develop a user-friendly web application supporting the federated averaging (FedAvg) algorithm, enabling users to configure parameters through an intuitive interface. The backend solution efficiently manages communication between the parameter server and edge nodes. We also implement model compression and scheduling algorithms to optimize FL performance. Furthermore, we explore intent-based automation in FL using a fine-tuned Language Model (LLM) trained on a tailored dataset, allowing users to conduct FL tasks using high-level prompts. We observe that the LLM-based automated solution achieves comparable test accuracy to the standard web-based solution while reducing transferred bytes by up to 64% and CPU time by up to 46% for FL tasks. Also, we leverage the neural architecture search (NAS) and hyperparameter optimization (HPO) using LLM to improve the performance. We observe that by using this approach test accuracy can be improved by 10-20% for the carried out FL tasks.

cs.LG↗

arXiv2024

Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix

In computer vision, the vision transformer (ViT) has increasingly superseded the convolutional neural network (CNN) for improved accuracy and robustness. However, ViT's large model sizes and high sample complexity make it difficult to train on resource-constrained edge devices. Split learning (SL) emerges as a viable solution, leveraging server-side resources to train ViTs while utilizing private data from distributed devices. However, SL requires additional information exchange for weight updates between the device and the server, which can be exposed to various attacks on private training data. To mitigate the risk of data breaches in classification tasks, inspired from the CutMix regularization, we propose a novel privacy-preserving SL framework that injects Gaussian noise into smashed data and mixes randomly chosen patches of smashed data across clients, coined DP-CutMixSL. Our analysis demonstrates that DP-CutMixSL is a differentially private (DP) mechanism that strengthens privacy protection against membership inference attacks during forward propagation. Through simulations, we show that DP-CutMixSL improves privacy protection against membership inference attacks, reconstruction attacks, and label inference attacks, while also improving accuracy compared to DP-SL and DP-MixSL.

cs.DC↗