Search Results for author: Mehdi Bennis

Found 119 papers, 10 papers with code

Language-Oriented Communication with Semantic Coding and Knowledge Distillation for Text-to-Image Generation

no code implementations20 Sep 2023 Hyelin Nam, Jihong Park, Jinho Choi, Mehdi Bennis, Seong-Lyun Kim

By integrating recent advances in large language models (LLMs) and generative models into the emerging semantic communication (SC) paradigm, in this article we put forward to a novel framework of language-oriented semantic communication (LSC).

Knowledge Distillation

Emergent Communication in Multi-Agent Reinforcement Learning for Future Wireless Networks

no code implementations12 Sep 2023 Marwa Chafii, Salmane Naoumi, REDA ALAMI, Ebtesam Almazrouei, Mehdi Bennis, Merouane Debbah

In different wireless network scenarios, multiple network entities need to cooperate in order to achieve a common task with minimum delay and energy consumption.

Autonomous Driving Continuous Control +4

Joint Semantic-Native Communication and Inference via Minimal Simplicial Structures

no code implementations31 Aug 2023 Qiyang Zhao, Hang Zou, Mehdi Bennis, Merouane Debbah, Ebtesam Almazrouei, Faouzi Bader

Specifically, the teacher first maps its data into a k-order simplicial complex and learns its high-order correlations.

Reasoning over the Air: A Reasoning-based Implicit Semantic-Aware Communication Framework

1 code implementation20 Jun 2023 Yong Xiao, Yiwei Liao, Yingyu Li, Guangming Shi, H. Vincent Poor, Walid Saad, Merouane Debbah, Mehdi Bennis

Most existing works focus on transmitting and delivering the explicit semantic meaning that can be directly identified from the source signal.

Imitation Learning

Cooperative Multi-Agent Learning for Navigation via Structured State Abstraction

no code implementations20 Jun 2023 Mohamed K. AbdelAziz, Mohammed S. Elbamby, Sumudu Samarakoon, Mehdi Bennis

Learning a navigation policy along with a communication protocol in a MARL environment is highly complex due to the huge state space to be explored.

Multi-agent Reinforcement Learning

Federated Learning Games for Reconfigurable Intelligent Surfaces via Causal Representations

no code implementations2 Jun 2023 Charbel Bou Chaaya, Sumudu Samarakoon, Mehdi Bennis

Equivalently, this corresponds to a game played between multiple RISs, as learning agents, in heterogeneous environments.

Federated Learning

Codesign of Edge Intelligence and Automated Guided Vehicle Control

1 code implementation3 May 2023 Malith Gallage, Rafaela Scaciota, Sumudu Samarakoon, Mehdi Bennis

This work presents a harmonic design of autonomous guided vehicle (AGV) control, edge intelligence, and human input to enable autonomous transportation in industrial environments.


Performance Analysis of ML-based MTC Traffic Pattern Predictors

no code implementations4 Apr 2023 David E. Ruiz-Guirola, Onel L. A. Lopez, Samuel Montejo-Sanchez, Richard Demo Souza, Mehdi Bennis

Herein, we assess the performance of several machine learning (ML) methods to predict Poisson and quasi-periodic MTC traffic in terms of accuracy and computational cost.

Making Sense of Meaning: A Survey on Metrics for Semantic and Goal-Oriented Communication

no code implementations20 Mar 2023 Tilahun M. Getu, Georges Kaddoum, Mehdi Bennis

Despite the surge in their swift development, the design, analysis, optimization, and realization of robust and intelligent SemCom as well as goal-oriented SemCom are fraught with many fundamental challenges.

Computation and Privacy Protection for Satellite-Ground Digital Twin Networks

no code implementations16 Feb 2023 Yongkang Gong, Haipeng Yao Xiaonan Liu, Mehdi Bennis, Arumugam Nallanathan, Zhu Han

Satellite-ground integrated digital twin networks (SGIDTNs) are regarded as innovative network architectures for reducing network congestion, enabling nearly-instant data mapping from the physical world to digital systems, and offering ubiquitous intelligence services to terrestrial users.


Performance Limits of a Deep Learning-Enabled Text Semantic Communication under Interference

no code implementations15 Feb 2023 Tilahun M. Getu, Walid Saad, Georges Kaddoum, Mehdi Bennis

To shed light on this knowledge gap and stimulate fundamental research on IR$^2$ SemCom, the performance limits of a text SemCom system named DeepSC are studied in the presence of (multi-interferer) RFI.

Adversarial Learning for Implicit Semantic-Aware Communications

no code implementations27 Jan 2023 Zhimin Lu, Yong Xiao, Zijian Sun, Yingyu Li, Guangming Shi, Xianfu Chen, Mehdi Bennis, H. Vincent Poor

In this paper, we consider the implicit semantic communication problem in which hidden relations and closely related semantic terms that cannot be recognized from the source signals need to also be delivered to the destination user.

Enabling the Wireless Metaverse via Semantic Multiverse Communication

no code implementations13 Dec 2022 Jihong Park, Jinho Choi, Seong-Lyun Kim, Mehdi Bennis

Metaverse over wireless networks is an emerging use case of the sixth generation (6G) wireless systems, posing unprecedented challenges in terms of its multi-modal data transmissions with stringent latency and reliability requirements.

Multi-agent Reinforcement Learning

Quantum Federated Learning with Entanglement Controlled Circuits and Superposition Coding

no code implementations4 Dec 2022 Won Joon Yun, Jae Pyoung Kim, Hankyul Baek, Soyi Jung, Jihong Park, Mehdi Bennis, Joongheon Kim

While witnessing the noisy intermediate-scale quantum (NISQ) era and beyond, quantum federated learning (QFL) has recently become an emerging field of study.

Federated Learning Image Classification

On the Energy and Communication Efficiency Tradeoffs in Federated and Multi-Task Learning

no code implementations2 Dec 2022 Stefano Savazzi, Vittorio Rampa, Sanaz Kianoush, Mehdi Bennis

The MTL process is carried out in two stages: the optimization of a meta-model that can be quickly adapted to learn new tasks, and a task-specific model adaptation stage where the learned meta-model is transferred to agents and tailored for a specific task.

Federated Learning Meta-Learning +2

Goal-Oriented Communications for the IoT and Application to Data Compression

no code implementations10 Nov 2022 Chao Zhang, Hang Zou, Samson Lasaulce, Walid Saad, Marios Kountouris, Mehdi Bennis

Internet of Things (IoT) devices will play an important role in emerging applications, since their sensing, actuation, processing, and wireless communication capabilities stimulate data collection, transmission and decision processes of smart applications.

Data Compression

Semantic-Native Communication: A Simplicial Complex Perspective

no code implementations30 Oct 2022 Qiyang Zhao, Mehdi Bennis, Merouane Debbah, Daniel Benevides da Costa

In this paper, we study semantic communication from a topological space perspective, in which higher-order data semantics live in a simplicial complex.

Differentially Private CutMix for Split Learning with Vision Transformer

no code implementations28 Oct 2022 Seungeun Oh, Jihong Park, Sihun Baek, Hyelin Nam, Praneeth Vepakomma, Ramesh Raskar, Mehdi Bennis, Seong-Lyun Kim

Split learning (SL) detours this by communicating smashed data at a cut-layer, yet suffers from data privacy leakage and large communication costs caused by high similarity between ViT' s smashed data and input data.

Federated Learning Privacy Preserving

Federated and Meta learning over Non-Wireless and Wireless Networks: A Tutorial

no code implementations24 Oct 2022 Xiaonan Liu, Yansha Deng, Arumugam Nallanathan, Mehdi Bennis

Typically, FL focuses on learning a global model for a given task and all devices and hence cannot adapt the model to devices with different data distributions.

Decision Making Federated Learning +2

Age of Semantics in Cooperative Communications: To Expedite Simulation Towards Real via Offline Reinforcement Learning

no code implementations19 Sep 2022 Xianfu Chen, Zhifeng Zhao, Shiwen Mao, Celimuge Wu, Honggang Zhang, Mehdi Bennis

We then put forward a novel offline DAC scheme, which estimates the optimal control policy from a previously collected dataset without any further interactions with the system.

Reinforcement Learning (RL)

DR-DSGD: A Distributionally Robust Decentralized Learning Algorithm over Graphs

no code implementations29 Aug 2022 Chaouki Ben Issaid, Anis Elgabli, Mehdi Bennis

In this paper, we propose to solve a regularized distributionally robust learning problem in the decentralized setting, taking into account the data distribution shift.

Terahertz-Band Integrated Sensing and Communications: Challenges and Opportunities

no code implementations2 Aug 2022 Ahmet M. Elbir, Kumar Vijay Mishra, Symeon Chatzinotas, Mehdi Bennis

The sixth generation (6G) wireless networks aim to achieve ultra-high data transmission rates, very low latency and enhanced energy-efficiency.

Slimmable Quantum Federated Learning

no code implementations20 Jul 2022 Won Joon Yun, Jae Pyoung Kim, Soyi Jung, Jihong Park, Mehdi Bennis, Joongheon Kim

Quantum federated learning (QFL) has recently received increasing attention, where quantum neural networks (QNNs) are integrated into federated learning (FL).

Federated Learning

Towards Semantic Communication Protocols: A Probabilistic Logic Perspective

no code implementations8 Jul 2022 Sejin Seo, Jihong Park, Seung-Woo Ko, Jinho Choi, Mehdi Bennis, Seong-Lyun Kim

Classical medium access control (MAC) protocols are interpretable, yet their task-agnostic control signaling messages (CMs) are ill-suited for emerging mission-critical applications.

An Energy and Carbon Footprint Analysis of Distributed and Federated Learning

no code implementations21 Jun 2022 Stefano Savazzi, Vittorio Rampa, Sanaz Kianoush, Mehdi Bennis

Classical and centralized Artificial Intelligence (AI) methods require moving data from producers (sensors, machines) to energy hungry data centers, raising environmental concerns due to computational and communication resource demands, while violating privacy.

Federated Learning

Computation Offloading and Resource Allocation in F-RANs: A Federated Deep Reinforcement Learning Approach

no code implementations13 Jun 2022 Lingling Zhang, Yanxiang Jiang, Fu-Chun Zheng, Mehdi Bennis, Xiaohu You

In this paper, by considering time-varying network environment, a dynamic computation offloading and resource allocation problem in F-RANs is formulated to minimize the task execution delay and energy consumption of MDs.

Federated Learning Reinforcement Learning (RL)

Content Popularity Prediction in Fog-RANs: A Clustered Federated Learning Based Approach

no code implementations13 Jun 2022 Zhiheng Wang, Yanxiang Jiang, Fu-Chun Zheng, Mehdi Bennis, Xiaohu You

Based on clustered federated learning, we propose a novel mobility-aware popularity prediction policy, which integrates content popularities in terms of local users and mobile users.

Federated Learning

Learning Generalized Wireless MAC Communication Protocols via Abstraction

no code implementations6 Jun 2022 Luciano Miuccio, Salvatore Riolo, Sumudu Samarakoony, Daniela Panno, Mehdi Bennis

To tackle the heterogeneous requirements of beyond 5G (B5G) and future 6G wireless networks, conventional medium access control (MAC) procedures need to evolve to enable base stations (BSs) and user equipments (UEs) to automatically learn innovative MAC protocols catering to extremely diverse services.

Reinforcement Learning (RL)

Pervasive Machine Learning for Smart Radio Environments Enabled by Reconfigurable Intelligent Surfaces

1 code implementation8 May 2022 George C. Alexandropoulos, Kyriakos Stylianopoulos, Chongwen Huang, Chau Yuen, Mehdi Bennis, Mérouane Debbah

The emerging technology of Reconfigurable Intelligent Surfaces (RISs) is provisioned as an enabler of smart wireless environments, offering a highly scalable, low-cost, hardware-efficient, and almost energy-neutral solution for dynamic control of the propagation of electromagnetic signals over the wireless medium, ultimately providing increased environmental intelligence for diverse operation objectives.

BIG-bench Machine Learning Multi-Armed Bandits

Time-triggered Federated Learning over Wireless Networks

no code implementations26 Apr 2022 Xiaokang Zhou, Yansha Deng, Huiyun Xia, Shaochuan Wu, Mehdi Bennis

The newly emerging federated learning (FL) framework offers a new way to train machine learning models in a privacy-preserving manner.

Federated Learning Privacy Preserving

SlimFL: Federated Learning with Superposition Coding over Slimmable Neural Networks

no code implementations26 Mar 2022 Won Joon Yun, Yunseok Kwak, Hankyul Baek, Soyi Jung, Mingyue Ji, Mehdi Bennis, Jihong Park, Joongheon Kim

However, applying FL in practice is challenging due to the local devices' heterogeneous energy, wireless channel conditions, and non-independently and identically distributed (non-IID) data distributions.

Distributed Computing Federated Learning

Variational Autoencoders for Reliability Optimization in Multi-Access Edge Computing Networks

no code implementations25 Jan 2022 Arian Ahmadi, Omid Semiari, Mehdi Bennis, Merouane Debbah

In this paper, a novel framework is proposed to optimize the reliability of MEC networks by considering the distribution of E2E service delay, encompassing over-the-air transmission and edge computing latency.


THz-Empowered UAVs in 6G: Opportunities, Challenges, and Trade-Offs

no code implementations13 Jan 2022 M. Mahdi Azari, Sourabh Solanki, Symeon Chatzinotas, Mehdi Bennis

Envisioned use cases of unmanned aerial vehicles (UAVs) impose new service requirements in terms of data rate, latency, and sensing accuracy, to name a few.

Attention Based Communication and Control for Multi-UAV Path Planning

no code implementations20 Dec 2021 Hamid Shiri, Hyowoon Seo, Jihong Park, Mehdi Bennis

Inspired by the multi-head attention (MHA) mechanism in natural language processing, this letter proposes an iterative single-head attention (ISHA) mechanism for multi-UAV path planning.

Decision Making

Communication and Energy Efficient Slimmable Federated Learning via Superposition Coding and Successive Decoding

no code implementations5 Dec 2021 Hankyul Baek, Won Joon Yun, Soyi Jung, Jihong Park, Mingyue Ji, Joongheon Kim, Mehdi Bennis

To address the heterogeneous communication throughput problem, each full-width (1. 0x) SNN model and its half-width ($0. 5$x) model are superposition-coded before transmission, and successively decoded after reception as the 0. 5x or $1. 0$x model depending on the channel quality.

Federated Learning

Joint Superposition Coding and Training for Federated Learning over Multi-Width Neural Networks

no code implementations5 Dec 2021 Hankyul Baek, Won Joon Yun, Yunseok Kwak, Soyi Jung, Mingyue Ji, Mehdi Bennis, Jihong Park, Joongheon Kim

By applying SC, SlimFL exchanges the superposition of multiple width configurations that are decoded as many as possible for a given communication throughput.

Federated Learning

Learning Emergent Random Access Protocol for LEO Satellite Networks

no code implementations3 Dec 2021 Ju-Hyung Lee, Hyowoon Seo, Jihong Park, Mehdi Bennis, Young-Chai Ko

A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems.


Learning, Computing, and Trustworthiness in Intelligent IoT Environments: Performance-Energy Tradeoffs

no code implementations4 Oct 2021 Beatriz Soret, Lam D. Nguyen, Jan Seeger, Arne Bröring, Chaouki Ben Issaid, Sumudu Samarakoon, Anis El Gabli, Vivek Kulkarni, Mehdi Bennis, Petar Popovski

An Intelligent IoT Environment (iIoTe) is comprised of heterogeneous devices that can collaboratively execute semi-autonomous IoT applications, examples of which include highly automated manufacturing cells or autonomously interacting harvesting machines.

Edge-computing Total Energy

Federated Distributionally Robust Optimization for Phase Configuration of RISs

no code implementations20 Aug 2021 Chaouki Ben Issaid, Sumudu Samarakoon, Mehdi Bennis, H. Vincent Poor

In this article, we study the problem of robust reconfigurable intelligent surface (RIS)-aided downlink communication over heterogeneous RIS types in the supervised learning setting.

Federated Learning with Correlated Data: Taming the Tail for Age-Optimal Industrial IoT

no code implementations17 Aug 2021 Chen-Feng Liu, Mehdi Bennis

While information delivery in industrial Internet of things demands reliability and latency guarantees, the freshness of the controller's available information, measured by the age of information (AoI), is paramount for high-performing industrial automation.

Federated Learning Model Selection

Semantics-Native Communication with Contextual Reasoning

no code implementations12 Aug 2021 Hyowoon Seo, Jihong Park, Mehdi Bennis, Mérouane Debbah

Spurred by a huge interest in the post-Shannon communication, it has recently been shown that leveraging semantics can significantly improve the communication effectiveness across many tasks.

Joint Client Scheduling and Resource Allocation under Channel Uncertainty in Federated Learning

no code implementations12 Jun 2021 Madhusanka Manimel Wadu, Sumudu Samarakoon, Mehdi Bennis

In this article we investigate the problem of client scheduling and resource block (RB) allocation to enhance the performance of model training using FL, over a pre-defined training duration under imperfect channel state information (CSI) and limited local computing resources.

Federated Learning Scheduling +1

Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels

no code implementations2 Jun 2021 Mounssif Krouka, Anis Elgabli, Chaouki Ben Issaid, Mehdi Bennis

In this paper, we propose a technique to reduce the total energy bill at the edge device by utilizing model compression and time-varying model split between the edge and remote nodes.

Collaborative Inference Image Classification +2

Communication-Efficient Split Learning Based on Analog Communication and Over the Air Aggregation

no code implementations2 Jun 2021 Mounssif Krouka, Anis Elgabli, Chaouki Ben Issaid, Mehdi Bennis

Split-learning (SL) has recently gained popularity due to its inherent privacy-preserving capabilities and ability to enable collaborative inference for devices with limited computational power.

Collaborative Inference Privacy Preserving

Attention-based Reinforcement Learning for Real-Time UAV Semantic Communication

no code implementations22 May 2021 Won Joon Yun, Byungju Lim, Soyi Jung, Young-Chai Ko, Jihong Park, Joongheon Kim, Mehdi Bennis

In this article, we study the problem of air-to-ground ultra-reliable and low-latency communication (URLLC) for a moving ground user.

Graph Attention reinforcement-learning +1

Robust Reconfigurable Intelligent Surfaces via Invariant Risk and Causal Representations

no code implementations4 May 2021 Sumudu Samarakoon, Jihong Park, Mehdi Bennis

In this paper, the problem of robust reconfigurable intelligent surface (RIS) system design under changes in data distributions is investigated.

AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning

no code implementations2 May 2021 Yusuke Koda, Jihong Park, Mehdi Bennis, Praneeth Vepakomma, Ramesh Raskar

In AirMixML, multiple workers transmit analog-modulated signals of their private data samples to an edge server who trains an ML model using the received noisy-and superpositioned samples.

BIG-bench Machine Learning Data Augmentation +1

Communication-Efficient and Personalized Federated Lottery Ticket Learning

no code implementations26 Apr 2021 Sejin Seo, Seung-Woo Ko, Jihong Park, Seong-Lyun Kim, Mehdi Bennis

The lottery ticket hypothesis (LTH) claims that a deep neural network (i. e., ground network) contains a number of subnetworks (i. e., winning tickets), each of which exhibiting identically accurate inference capability as that of the ground network.

Federated Learning Multi-Task Learning

Split Learning Meets Koopman Theory for Wireless Remote Monitoring and Prediction

no code implementations16 Apr 2021 Abanoub M. Girgis, Hyowoon Seo, Jihong Park, Mehdi Bennis, Jinho Choi

Numerical results under a non-linear cart-pole environment demonstrate that the proposed split learning of a Koopman autoencoder can locally predict future states, and the prediction accuracy increases with the representation dimension and transmission power.

UAV-Assisted Communication in Remote Disaster Areas using Imitation Learning

no code implementations2 Apr 2021 Alireza Shamsoshoara, Fatemeh Afghah, Erik Blasch, Jonathan Ashdown, Mehdi Bennis

The damage to cellular towers during natural and man-made disasters can disturb the communication services for cellular users.

Imitation Learning Scheduling

Ultra-Reliable Indoor Millimeter Wave Communications using Multiple Artificial Intelligence-Powered Intelligent Surfaces

no code implementations31 Mar 2021 Mehdi Naderi Soorki, Walid Saad, Mehdi Bennis, Choong Seon Hong

Simulation results show that the error between policies of the optimal and the RNN-based controllers is less than 1. 5%.

A Framework for Energy and Carbon Footprint Analysis of Distributed and Federated Edge Learning

3 code implementations18 Mar 2021 Stefano Savazzi, Sanaz Kianoush, Vittorio Rampa, Mehdi Bennis

Recent advances in distributed learning raise environmental concerns due to the large energy needed to train and move data to/from data centers.

Federated Learning

Seven Defining Features of Terahertz (THz) Wireless Systems: A Fellowship of Communication and Sensing

no code implementations15 Feb 2021 Christina Chaccour, Mehdi Naderi Soorki, Walid Saad, Mehdi Bennis, Petar Popovski, Merouane Debbah

Based on these fundamentals, we characterize seven unique defining features of THz wireless systems: 1) Quasi-opticality of the band, 2) THz-tailored wireless architectures, 3) Synergy with lower frequency bands, 4) Joint sensing and communication systems, 5) PHY-layer procedures, 6) Spectrum access techniques, and 7) Real-time network optimization.

Information Theory Information Theory

Federated Learning on the Road: Autonomous Controller Design for Connected and Autonomous Vehicles

no code implementations5 Feb 2021 Tengchan Zeng, Omid Semiari, Mingzhe Chen, Walid Saad, Mehdi Bennis

The results also validate the feasibility of the contract-theoretic incentive mechanism and show that the proposed mechanism can improve the convergence speed of the DFP algorithm by 40% compared to the baselines.

Autonomous Vehicles Federated Learning

Distributed Conditional Generative Adversarial Networks (GANs) for Data-Driven Millimeter Wave Communications in UAV Networks

no code implementations2 Feb 2021 Qianqian Zhang, Aidin Ferdowsi, Walid Saad, Mehdi Bennis

To guarantee an efficient learning process, necessary and sufficient conditions for the optimal UAV network topology that maximizes the learning rate for cooperative channel modeling are derived, and the optimal CGAN learning solution per UAV is subsequently characterized, based on the distributed network structure.

Robust Blockchained Federated Learning with Model Validation and Proof-of-Stake Inspired Consensus

1 code implementation9 Jan 2021 Hang Chen, Syed Ali Asif, Jihong Park, Chien-Chung Shen, Mehdi Bennis

Federated learning (FL) is a promising distributed learning solution that only exchanges model parameters without revealing raw data.

Federated Learning

Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems

2 code implementations9 Jan 2021 Stefano Savazzi, Monica Nicoli, Mehdi Bennis, Sanaz Kianoush, Luca Barbieri

Next-generation autonomous and networked industrial systems (i. e., robots, vehicles, drones) have driven advances in ultra-reliable, low latency communications (URLLC) and computing.

Federated Learning

Predictive Ultra-Reliable Communication: A Survival Analysis Perspective

no code implementations22 Dec 2020 Sumudu Samarakoon, Mehdi Bennis, Walid Saad, Merouane Debbah

Results show that the accuracy of detecting channel blocking events is higher using the model-based method for low to moderate reliability targets requiring low sample complexity.

Survival Analysis Networking and Internet Architecture

Vehicular Cooperative Perception Through Action Branching and Federated Reinforcement Learning

no code implementations7 Dec 2020 Mohamed K. Abdel-Aziz, Cristina Perfecto, Sumudu Samarakoon, Mehdi Bennis, Walid Saad

Simulation results show the ability of the RL agents to efficiently learn the vehicles' association, RB allocation, and message content selection while maximizing vehicles' satisfaction in terms of the received sensory information.

reinforcement-learning Reinforcement Learning (RL)

BayGo: Joint Bayesian Learning and Information-Aware Graph Optimization

no code implementations9 Nov 2020 Tamara Alshammari, Sumudu Samarakoon, Anis Elgabli, Mehdi Bennis

This article deals with the problem of distributed machine learning, in which agents update their models based on their local datasets, and aggregate the updated models collaboratively and in a fully decentralized manner.

Federated Knowledge Distillation

3 code implementations4 Nov 2020 Hyowoon Seo, Jihong Park, Seungeun Oh, Mehdi Bennis, Seong-Lyun Kim

The goal of this chapter is to provide a deep understanding of FD while demonstrating its communication efficiency and applicability to a variety of tasks.

Federated Learning Knowledge Distillation

Distributional Reinforcement Learning for mmWave Communications with Intelligent Reflectors on a UAV

no code implementations3 Nov 2020 Qianqian Zhang, Walid Saad, Mehdi Bennis

In this paper, a novel communication framework that uses an unmanned aerial vehicle (UAV)-carried intelligent reflector (IR) is proposed to enhance multi-user downlink transmissions over millimeter wave (mmWave) frequencies.

Distributional Reinforcement Learning reinforcement-learning +1

Integrating LEO Satellites and Multi-UAV Reinforcement Learning for Hybrid FSO/RF Non-Terrestrial Networks

no code implementations20 Oct 2020 Ju-Hyung Lee, Jihong Park, Mehdi Bennis, Young-Chai Ko

Lastly, thanks to utilizing hybrid FSO/RF links, the proposed scheme achieves up to 62. 56x higher peak throughput and 21. 09x higher worst-case throughput than the cases utilizing either RF or FSO links, highlighting the importance of co-designing SAT-UAV associations, UAV trajectories, and hybrid FSO/RF links in beyond-5G NTNs.

Dimensionality Reduction Reinforcement Learning (RL)

When Wireless Communications Meet Computer Vision in Beyond 5G

no code implementations13 Oct 2020 Takayuki Nishio, Yusuke Koda, Jihong Park, Mehdi Bennis, Klaus Doppler

This article articulates the emerging paradigm, sitting at the confluence of computer vision and wireless communication, to enable beyond-5G/6G mission-critical applications (autonomous/remote-controlled vehicles, visuo-haptic VR, and other cyber-physical applications).

Image Reconstruction

Phase Configuration Learning in Wireless Networks with Multiple Reconfigurable Intelligent Surfaces

no code implementations9 Oct 2020 George C. Alexandropoulos, Sumudu Samarakoon, Mehdi Bennis, Merouane Debbah

Reconfigurable Intelligent Surfaces (RISs) are recently gaining remarkable attention as a low-cost, hardware-efficient, and highly scalable technology capable of offering dynamic control of electro-magnetic wave propagation.

Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels

no code implementations8 Oct 2020 Dingzhu Wen, Ki-Jun Jeon, Mehdi Bennis, Kaibin Huang

Targeting broadband channels, we consider the joint control of parameter allocation, sub-channel allocation, and transmission power to improve the performance of PARTEL.

Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMM

no code implementations14 Sep 2020 Chaouki Ben Issaid, Anis Elgabli, Jihong Park, Mehdi Bennis, Mérouane Debbah

In this paper, we propose a communication-efficiently decentralized machine learning framework that solves a consensus optimization problem defined over a network of inter-connected workers.


Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning

no code implementations3 Jul 2020 Anis Elgabli, Jihong Park, Chaouki Ben Issaid, Mehdi Bennis

Wireless connectivity is instrumental in enabling scalable federated learning (FL), yet wireless channels bring challenges for model training, in which channel randomness perturbs each worker's model update while multiple workers' updates incur significant interference under limited bandwidth.

Federated Learning Privacy Preserving

Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup

no code implementations17 Jun 2020 Seungeun Oh, Jihong Park, Eunjeong Jeong, Hyesung Kim, Mehdi Bennis, Seong-Lyun Kim

This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD.

Federated Learning Privacy Preserving

XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning

no code implementations9 Jun 2020 MyungJae Shin, Chihoon Hwang, Joongheon Kim, Jihong Park, Mehdi Bennis, Seong-Lyun Kim

User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL).

Data Augmentation Federated Learning +1

Federated Learning in Vehicular Networks

no code implementations2 Jun 2020 Ahmet M. Elbir, Burak Soner, Sinem Coleri, Deniz Gunduz, Mehdi Bennis

Machine learning (ML) has recently been adopted in vehicular networks for applications such as autonomous driving, road safety prediction and vehicular object detection, due to its model-free characteristic, allowing adaptive fast response.

Autonomous Driving Federated Learning +3

Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning

no code implementations13 May 2020 Han Cha, Jihong Park, Hyesung Kim, Mehdi Bennis, Seong-Lyun Kim

Traditional distributed deep reinforcement learning (RL) commonly relies on exchanging the experience replay memory (RM) of each agent.

Clustering Data Augmentation +3

Deep Learning Assisted CSI Estimation for Joint URLLC and eMBB Resource Allocation

no code implementations12 Mar 2020 Hamza Khan, M. Majid Butt, Sumudu Samarakoon, Philippe Sehier, Mehdi Bennis

Multiple-input multiple-output (MIMO) is a key for the fifth generation (5G) and beyond wireless communication systems owing to higher spectrum efficiency, spatial gains, and energy efficiency.

Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learning

no code implementations10 Mar 2020 Dingzhu Wen, Mehdi Bennis, Kaibin Huang

To this end, in each iteration, the model is dynamically partitioned into parametric blocks, which are downloaded to worker groups for updating using data subsets.

Communication-Efficient Massive UAV Online Path Control: Federated Learning Meets Mean-Field Game Theory

no code implementations9 Mar 2020 Hamid Shiri, Jihong Park, Mehdi Bennis

Therefore, the federated learning (FL) approach which can share the model parameters of NNs at drones, is proposed with NN based MFG to satisfy the required conditions.

Federated Learning

Millimeter Wave Communications with an Intelligent Reflector: Performance Optimization and Distributional Reinforcement Learning

no code implementations24 Feb 2020 Qianqian Zhang, Walid Saad, Mehdi Bennis

Furthermore, under limited knowledge of CSI, simulation results show that the proposed QR-DRL method, which learns a full distribution of the downlink rate, yields a better prediction accuracy and improves the downlink rate by 10% for online deployments, compared with a Q-learning baseline.

Distributional Reinforcement Learning Q-Learning +2

Federated Learning in the Sky: Joint Power Allocation and Scheduling with UAV Swarms

no code implementations19 Feb 2020 Tengchan Zeng, Omid Semiari, Mohammad Mozaffari, Mingzhe Chen, Walid Saad, Mehdi Bennis

Unmanned aerial vehicle (UAV) swarms must exploit machine learning (ML) in order to execute various tasks ranging from coordinated trajectory planning to cooperative target recognition.

Federated Learning Scheduling +1

Federated Learning under Channel Uncertainty: Joint Client Scheduling and Resource Allocation

no code implementations3 Feb 2020 Madhusanka Manimel Wadu, Sumudu Samarakoon, Mehdi Bennis

In this work, we propose a novel joint client scheduling and resource block (RB) allocation policy to minimize the loss of accuracy in federated learning (FL) over wireless compared to a centralized training-based solution, under imperfect channel state information (CSI).

Networking and Internet Architecture

Cellular-Connected Wireless Virtual Reality: Requirements, Challenges, and Solutions

no code implementations13 Jan 2020 Fenghe Hu, Yansha Deng, Walid Saad, Mehdi Bennis, A. Hamid Aghvami

Cellular-connected wireless connectivity provides new opportunities for virtual reality(VR) to offer seamless user experience from anywhere at anytime.

Ultra-Reliable and Low-Latency Vehicular Communication: An Active Learning Approach

no code implementations27 Nov 2019 Mohamed K. Abdel-Aziz, Sumudu Samarakoon, Mehdi Bennis, Walid Saad

Therefore, to effectively allocate power and RBs, the proposed approach allows the network to actively learn its dynamics by balancing a tradeoff between minimizing the probability that the vehicles' AoI exceeds a predefined threshold and maximizing the knowledge about the network dynamics.

Active Learning GPR

L-FGADMM: Layer-Wise Federated Group ADMM for Communication Efficient Decentralized Deep Learning

no code implementations9 Nov 2019 Anis Elgabli, Jihong Park, Sabbir Ahmed, Mehdi Bennis

This article proposes a communication-efficient decentralized deep learning algorithm, coined layer-wise federated group ADMM (L-FGADMM).

Federated Learning

Remote UAV Online Path Planning via Neural Network Based Opportunistic Control

no code implementations11 Oct 2019 Hamid Shiri, Jihong Park, Mehdi Bennis

This letter proposes a neural network (NN) aided remote unmanned aerial vehicle (UAV) online control algorithm, coined oHJB.

GADMM: Fast and Communication Efficient Framework for Distributed Machine Learning

no code implementations30 Aug 2019 Anis Elgabli, Jihong Park, Amrit S. Bedi, Mehdi Bennis, Vaneet Aggarwal

When the data is distributed across multiple servers, lowering the communication cost between the servers (or workers) while solving the distributed learning problem is an important problem and is the focus of this paper.

BIG-bench Machine Learning

Age of Information-Aware Radio Resource Management in Vehicular Networks: A Proactive Deep Reinforcement Learning Perspective

no code implementations6 Aug 2019 Xianfu Chen, Celimuge Wu, Tao Chen, Honggang Zhang, Zhi Liu, Yan Zhang, Mehdi Bennis

In this paper, we investigate the problem of age of information (AoI)-aware radio resource management for expected long-term performance optimization in a Manhattan grid vehicle-to-vehicle network.

Decision Making Management +1

Federated Reinforcement Distillation with Proxy Experience Memory

no code implementations15 Jul 2019 Han Cha, Jihong Park, Hyesung Kim, Seong-Lyun Kim, Mehdi Bennis

In distributed reinforcement learning, it is common to exchange the experience memory of each agent and thereby collectively train their local models.

Privacy Preserving reinforcement-learning +1

Multi-hop Federated Private Data Augmentation with Sample Compression

no code implementations15 Jul 2019 Eunjeong Jeong, Seungeun Oh, Jihong Park, Hyesung Kim, Mehdi Bennis, Seong-Lyun Kim

On-device machine learning (ML) has brought about the accessibility to a tremendous amount of data from the users while keeping their local data private instead of storing it in a central entity.

Data Augmentation

Massive Autonomous UAV Path Planning: A Neural Network Based Mean-Field Game Theoretic Approach

no code implementations10 May 2019 Hamid Shiri, Jihong Park, Mehdi Bennis

Afterwards, each UAV can control its acceleration by locally solving two partial differential equations (PDEs), known as the Hamilton-Jacobi-Bellman (HJB) and Fokker-Planck-Kolmogorov (FPK) equations.

Wireless Network Intelligence at the Edge

no code implementations7 Dec 2018 Jihong Park, Sumudu Samarakoon, Mehdi Bennis, Mérouane Debbah

), requires a novel paradigm change calling for distributed, low-latency and reliable ML at the wireless network edge (referred to as edge ML).

Face Recognition Medical Diagnosis

Blockchained On-Device Federated Learning

2 code implementations12 Aug 2018 Hyesung Kim, Jihong Park, Mehdi Bennis, Seong-Lyun Kim

By leveraging blockchain, this letter proposes a blockchained federated learning (BlockFL) architecture where local learning model updates are exchanged and verified.

Information Theory Networking and Internet Architecture Information Theory

Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications

no code implementations21 Jul 2018 Sumudu Samarakoon, Mehdi Bennis, Walid Saad, Merouane Debbah

In this paper, the problem of joint power and resource allocation (JPRA) for ultra-reliable low-latency communication (URLLC) in vehicular networks is studied.

Information Theory Information Theory

Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning

no code implementations16 May 2018 Xianfu Chen, Honggang Zhang, Celimuge Wu, Shiwen Mao, Yusheng Ji, Mehdi Bennis

To improve the quality of computation experience for mobile devices, mobile-edge computing (MEC) is a promising paradigm by providing computing capabilities in close proximity within a sliced radio access network (RAN), which supports both traditional communication and MEC services.

Edge-computing reinforcement-learning +1

Federated Learning for Ultra-Reliable Low-Latency V2V Communications

no code implementations11 May 2018 Sumudu Samarakoon, Mehdi Bennis, Walid Saad, Merouane Debbah

It is shown that FL enables the proposed distributed method to estimate the tail distribution of queues with an accuracy that is very close to a centralized solution with up to 79\% reductions in the amount of data that need to be exchanged.

Federated Learning

Context-Aware Mobility Management in HetNets: A Reinforcement Learning Approach

no code implementations7 May 2015 Meryem Simsek, Mehdi Bennis, Ismail Güvenc

The use of small cell deployments in heterogeneous network (HetNet) environments is expected to be a key feature of 4G networks and beyond, and essential for providing higher user throughput and cell-edge coverage.

Fairness Management +3

Backhaul-Aware Interference Management in the Uplink of Wireless Small Cell Networks

no code implementations27 Aug 2013 Sumudu Samarakoon, Mehdi Bennis, Walid Saad, Matti Latva-aho

In this paper, a novel, backhaul-aware approach to interference management in wireless small cell networks is proposed.


Cannot find the paper you are looking for? You can Submit a new open access paper.