Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Mehdi Bennis

Mehdi Bennis

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


May 02, 2021
Yusuke Koda, Jihong Park, Mehdi Bennis, Praneeth Vepakomma, Ramesh Raskar

* 6 pages, 6 figures 
  Access Paper or Ask Questions

Communication-Efficient and Personalized Federated Lottery Ticket Learning


Apr 26, 2021
Sejin Seo, Seung-Woo Ko, Jihong Park, Seong-Lyun Kim, Mehdi Bennis

Figure 1 for Communication-Efficient and Personalized Federated Lottery Ticket Learning
Figure 2 for Communication-Efficient and Personalized Federated Lottery Ticket Learning
Figure 3 for Communication-Efficient and Personalized Federated Lottery Ticket Learning
Figure 4 for Communication-Efficient and Personalized Federated Lottery Ticket Learning
* 5 pages, 2 figures, 2 tables 
  Access Paper or Ask Questions

Split Learning Meets Koopman Theory for Wireless Remote Monitoring and Prediction


Apr 16, 2021
Abanoub M. Girgis, Hyowoon Seo, Jihong Park, Mehdi Bennis, Jinho Choi


  Access Paper or Ask Questions

Distributed Learning in Wireless Networks: Recent Progress and Future Challenges


Apr 05, 2021
Mingzhe Chen, Deniz Gündüz, Kaibin Huang, Walid Saad, Mehdi Bennis, Aneta Vulgarakis Feljan, H. Vincent Poor

Figure 1 for Distributed Learning in Wireless Networks: Recent Progress and Future Challenges
Figure 2 for Distributed Learning in Wireless Networks: Recent Progress and Future Challenges
Figure 3 for Distributed Learning in Wireless Networks: Recent Progress and Future Challenges
Figure 4 for Distributed Learning in Wireless Networks: Recent Progress and Future Challenges

  Access Paper or Ask Questions

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


Mar 31, 2021
Mehdi Naderi Soorki, Walid Saad, Mehdi Bennis, Choong Seon Hong

Figure 1 for Ultra-Reliable Indoor Millimeter Wave Communications using Multiple Artificial Intelligence-Powered Intelligent Surfaces
Figure 2 for Ultra-Reliable Indoor Millimeter Wave Communications using Multiple Artificial Intelligence-Powered Intelligent Surfaces
Figure 3 for Ultra-Reliable Indoor Millimeter Wave Communications using Multiple Artificial Intelligence-Powered Intelligent Surfaces
Figure 4 for Ultra-Reliable Indoor Millimeter Wave Communications using Multiple Artificial Intelligence-Powered Intelligent Surfaces

  Access Paper or Ask Questions

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


Mar 18, 2021
Stefano Savazzi, Sanaz Kianoush, Vittorio Rampa, Mehdi Bennis

* The work has been submitted to the IEEE for possible publication 
  Access Paper or Ask Questions

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


Feb 05, 2021
Tengchan Zeng, Omid Semiari, Mingzhe Chen, Walid Saad, Mehdi Bennis

Figure 1 for Federated Learning on the Road: Autonomous Controller Design for Connected and Autonomous Vehicles
Figure 2 for Federated Learning on the Road: Autonomous Controller Design for Connected and Autonomous Vehicles
Figure 3 for Federated Learning on the Road: Autonomous Controller Design for Connected and Autonomous Vehicles
Figure 4 for Federated Learning on the Road: Autonomous Controller Design for Connected and Autonomous Vehicles
* 30 pages, 6 figures 
  Access Paper or Ask Questions

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


Feb 02, 2021
Qianqian Zhang, Aidin Ferdowsi, Walid Saad, Mehdi Bennis

Figure 1 for Distributed Conditional Generative Adversarial Networks (GANs) for Data-Driven Millimeter Wave Communications in UAV Networks
Figure 2 for Distributed Conditional Generative Adversarial Networks (GANs) for Data-Driven Millimeter Wave Communications in UAV Networks
Figure 3 for Distributed Conditional Generative Adversarial Networks (GANs) for Data-Driven Millimeter Wave Communications in UAV Networks
Figure 4 for Distributed Conditional Generative Adversarial Networks (GANs) for Data-Driven Millimeter Wave Communications in UAV Networks

  Access Paper or Ask Questions

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


Jan 12, 2021
Stefano Savazzi, Monica Nicoli, Mehdi Bennis, Sanaz Kianoush, Luca Barbieri

Figure 1 for Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems
Figure 2 for Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems
Figure 3 for Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems
Figure 4 for Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems
* The paper has been accepted for publication in the IEEE Communications Magazine. The current arXiv contains an additional Appendix that describes the dataset for the setup of Fig. 5 
  Access Paper or Ask Questions

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


Jan 09, 2021
Hang Chen, Syed Ali Asif, Jihong Park, Chien-Chung Shen, Mehdi Bennis

Figure 1 for Robust Blockchained Federated Learning with Model Validation and Proof-of-Stake Inspired Consensus
Figure 2 for Robust Blockchained Federated Learning with Model Validation and Proof-of-Stake Inspired Consensus
Figure 3 for Robust Blockchained Federated Learning with Model Validation and Proof-of-Stake Inspired Consensus
Figure 4 for Robust Blockchained Federated Learning with Model Validation and Proof-of-Stake Inspired Consensus
* 8 pages, 7 figures, AAAI 2021 Workshop - Towards Robust, Secure and Efficient Machine Learning 
  Access Paper or Ask Questions

Vehicular Cooperative Perception Through Action Branching and Federated Reinforcement Learning


Dec 07, 2020
Mohamed K. Abdel-Aziz, Cristina Perfecto, Sumudu Samarakoon, Mehdi Bennis, Walid Saad

Figure 1 for Vehicular Cooperative Perception Through Action Branching and Federated Reinforcement Learning
Figure 2 for Vehicular Cooperative Perception Through Action Branching and Federated Reinforcement Learning
Figure 3 for Vehicular Cooperative Perception Through Action Branching and Federated Reinforcement Learning
Figure 4 for Vehicular Cooperative Perception Through Action Branching and Federated Reinforcement Learning
* 29 pages (single column, double space), 8 figures, Under review for possible publication in IEEE Transactions on Communication 
  Access Paper or Ask Questions

Cross Layer Optimization and Distributed Reinforcement Learning Approach for Tile-Based 360 Degree Wireless Video Streaming


Nov 12, 2020
Mounssif Krouka, Anis Elgabli, Mohammed S. Elbamby, Cristina Perfecto, Mehdi Bennis, Vaneet Aggarwal

Figure 1 for Cross Layer Optimization and Distributed Reinforcement Learning Approach for Tile-Based 360 Degree Wireless Video Streaming
Figure 2 for Cross Layer Optimization and Distributed Reinforcement Learning Approach for Tile-Based 360 Degree Wireless Video Streaming
Figure 3 for Cross Layer Optimization and Distributed Reinforcement Learning Approach for Tile-Based 360 Degree Wireless Video Streaming
Figure 4 for Cross Layer Optimization and Distributed Reinforcement Learning Approach for Tile-Based 360 Degree Wireless Video Streaming

  Access Paper or Ask Questions

BayGo: Joint Bayesian Learning and Information-Aware Graph Optimization


Nov 09, 2020
Tamara Alshammari, Sumudu Samarakoon, Anis Elgabli, Mehdi Bennis

Figure 1 for BayGo: Joint Bayesian Learning and Information-Aware Graph Optimization
Figure 2 for BayGo: Joint Bayesian Learning and Information-Aware Graph Optimization
Figure 3 for BayGo: Joint Bayesian Learning and Information-Aware Graph Optimization
Figure 4 for BayGo: Joint Bayesian Learning and Information-Aware Graph Optimization
* 6 pages, 5 figures, conference 
  Access Paper or Ask Questions

Federated Knowledge Distillation


Nov 04, 2020
Hyowoon Seo, Jihong Park, Seungeun Oh, Mehdi Bennis, Seong-Lyun Kim

Figure 1 for Federated Knowledge Distillation
Figure 2 for Federated Knowledge Distillation
Figure 3 for Federated Knowledge Distillation
Figure 4 for Federated Knowledge Distillation
* 30 pages, 12 figures, 2 tables; This chapter is written for the forthcoming book, Machine Learning and Wireless Communications (Cambridge University Press), edited by H. V. Poor, D. Gunduz, A. Goldsmith, and Y. Eldar 
  Access Paper or Ask Questions

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


Nov 03, 2020
Qianqian Zhang, Walid Saad, Mehdi Bennis

Figure 1 for Distributional Reinforcement Learning for mmWave Communications with Intelligent Reflectors on a UAV
Figure 2 for Distributional Reinforcement Learning for mmWave Communications with Intelligent Reflectors on a UAV
Figure 3 for Distributional Reinforcement Learning for mmWave Communications with Intelligent Reflectors on a UAV

  Access Paper or Ask Questions

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


Oct 20, 2020
Ju-Hyung Lee, Jihong Park, Mehdi Bennis, Young-Chai Ko

Figure 1 for Integrating LEO Satellites and Multi-UAV Reinforcement Learning for Hybrid FSO/RF Non-Terrestrial Networks
Figure 2 for Integrating LEO Satellites and Multi-UAV Reinforcement Learning for Hybrid FSO/RF Non-Terrestrial Networks
Figure 3 for Integrating LEO Satellites and Multi-UAV Reinforcement Learning for Hybrid FSO/RF Non-Terrestrial Networks
Figure 4 for Integrating LEO Satellites and Multi-UAV Reinforcement Learning for Hybrid FSO/RF Non-Terrestrial Networks

  Access Paper or Ask Questions

When Wireless Communications Meet Computer Vision in Beyond 5G


Oct 13, 2020
Takayuki Nishio, Yusuke Koda, Jihong Park, Mehdi Bennis, Klaus Doppler

Figure 1 for When Wireless Communications Meet Computer Vision in Beyond 5G
Figure 2 for When Wireless Communications Meet Computer Vision in Beyond 5G
Figure 3 for When Wireless Communications Meet Computer Vision in Beyond 5G
Figure 4 for When Wireless Communications Meet Computer Vision in Beyond 5G
* 7 pages, 4 figures; This work has been submitted to IEEE Communications Standards Magazine for possible publication 
  Access Paper or Ask Questions

Phase Configuration Learning in Wireless Networks with Multiple Reconfigurable Intelligent Surfaces


Oct 09, 2020
George C. Alexandropoulos, Sumudu Samarakoon, Mehdi Bennis, Merouane Debbah

Figure 1 for Phase Configuration Learning in Wireless Networks with Multiple Reconfigurable Intelligent Surfaces
Figure 2 for Phase Configuration Learning in Wireless Networks with Multiple Reconfigurable Intelligent Surfaces
Figure 3 for Phase Configuration Learning in Wireless Networks with Multiple Reconfigurable Intelligent Surfaces
Figure 4 for Phase Configuration Learning in Wireless Networks with Multiple Reconfigurable Intelligent Surfaces
* 6 pages, 6 figures, accepted to IEEE GLOBECOM 2020 
  Access Paper or Ask Questions

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


Oct 08, 2020
Dingzhu Wen, Ki-Jun Jeon, Mehdi Bennis, Kaibin Huang

Figure 1 for Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels
Figure 2 for Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels
Figure 3 for Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels
Figure 4 for Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels

  Access Paper or Ask Questions

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


Sep 14, 2020
Chaouki Ben Issaid, Anis Elgabli, Jihong Park, Mehdi Bennis

Figure 1 for Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMM
Figure 2 for Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMM
Figure 3 for Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMM
Figure 4 for Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMM
* 39 pages, 6 figures 
  Access Paper or Ask Questions

Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications


Aug 06, 2020
Jihong Park, Sumudu Samarakoon, Anis Elgabli, Joongheon Kim, Mehdi Bennis, Seong-Lyun Kim, Mérouane Debbah

Figure 1 for Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications
Figure 2 for Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications
Figure 3 for Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications
Figure 4 for Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications
* 20 pages, 14 figures; This article has been submitted to IEEE for possible publication 
  Access Paper or Ask Questions

Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems


Jul 15, 2020
Xianfu Chen, Celimuge Wu, Tao Chen, Zhi Liu, Honggang Zhang, Mehdi Bennis, Hang Liu, Yusheng Ji

Figure 1 for Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems
Figure 2 for Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems
Figure 3 for Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems
Figure 4 for Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems

  Access Paper or Ask Questions

Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning


Jul 03, 2020
Anis Elgabli, Jihong Park, Chaouki Ben Issaid, Mehdi Bennis

Figure 1 for Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning
Figure 2 for Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning
Figure 3 for Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning
Figure 4 for Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning

  Access Paper or Ask Questions

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


Jun 17, 2020
Seungeun Oh, Jihong Park, Eunjeong Jeong, Hyesung Kim, Mehdi Bennis, Seong-Lyun Kim

Figure 1 for Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup
Figure 2 for Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup
Figure 3 for Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup
Figure 4 for Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup
* 5 pages, 3 figures, 3 tables, accepted to IEEE Communications Letters 
  Access Paper or Ask Questions

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


Jun 09, 2020
MyungJae Shin, Chihoon Hwang, Joongheon Kim, Jihong Park, Mehdi Bennis, Seong-Lyun Kim

Figure 1 for XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning
Figure 2 for XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning
Figure 3 for XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning
Figure 4 for XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning

  Access Paper or Ask Questions

Integrating LEO Satellite and UAV Relaying via Reinforcement Learning for Non-Terrestrial Networks


May 26, 2020
Ju-Hyung Lee, Jihong Park, Mehdi Bennis, Young-Chai Ko

Figure 1 for Integrating LEO Satellite and UAV Relaying via Reinforcement Learning for Non-Terrestrial Networks
Figure 2 for Integrating LEO Satellite and UAV Relaying via Reinforcement Learning for Non-Terrestrial Networks
Figure 3 for Integrating LEO Satellite and UAV Relaying via Reinforcement Learning for Non-Terrestrial Networks
Figure 4 for Integrating LEO Satellite and UAV Relaying via Reinforcement Learning for Non-Terrestrial Networks

  Access Paper or Ask Questions

Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning


May 15, 2020
Han Cha, Jihong Park, Hyesung Kim, Mehdi Bennis, Seong-Lyun Kim

Figure 1 for Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning
Figure 2 for Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning
Figure 3 for Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning
Figure 4 for Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning
* 8 pages, 5 figures, This paper is accepted to IEEE Intelligent Systems special issue of July/Aug 2020 - Federated Machine Learning 
  Access Paper or Ask Questions

Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Leargning


May 13, 2020
Han Cha, Jihong Park, Hyesung Kim, Mehdi Bennis, Seong-Lyun Kim

Figure 1 for Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Leargning
Figure 2 for Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Leargning
Figure 3 for Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Leargning
Figure 4 for Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Leargning
* 8 pages, 5 figures, This paper is accepted to IEEE Intelligent Systems special issue of July/Aug 2020 - Federated Machine Learning 
  Access Paper or Ask Questions

6G White Paper on Edge Intelligence


Apr 30, 2020
Ella Peltonen, Mehdi Bennis, Michele Capobianco, Merouane Debbah, Aaron Ding, Felipe Gil-Castiñeira, Marko Jurmu, Teemu Karvonen, Markus Kelanti, Adrian Kliks, Teemu Leppänen, Lauri Lovén, Tommi Mikkonen, Ashwin Rao, Sumudu Samarakoon, Kari Seppänen, Paweł Sroka, Sasu Tarkoma, Tingting Yang

Figure 1 for 6G White Paper on Edge Intelligence
Figure 2 for 6G White Paper on Edge Intelligence
Figure 3 for 6G White Paper on Edge Intelligence
Figure 4 for 6G White Paper on Edge Intelligence

  Access Paper or Ask Questions

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


Mar 12, 2020
Hamza Khan, M. Majid Butt, Sumudu Samarakoon, Philippe Sehier, Mehdi Bennis

Figure 1 for Deep Learning Assisted CSI Estimation for Joint URLLC and eMBB Resource Allocation
Figure 2 for Deep Learning Assisted CSI Estimation for Joint URLLC and eMBB Resource Allocation
Figure 3 for Deep Learning Assisted CSI Estimation for Joint URLLC and eMBB Resource Allocation
Figure 4 for Deep Learning Assisted CSI Estimation for Joint URLLC and eMBB Resource Allocation
* 6 Pages, 5 Figures, Accepted for publication in: IEEE ICC 2020 Workshop on Ultra-high speed, Low latency and Massive Communication for futuristic 6G Networks (ULMC6GN) 
  Access Paper or Ask Questions