Mounssif Krouka

University of Oulu

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Mehdi Bennis

University of Oulu

Anis Elgabli

King Fahd University of Petroleum and Minerals

Chaouki Ben Issaid

University of Oulu

Mohammed S. Elbamby

Telefonica Research and Development

Vaneet Aggarwal

Purdue University West Lafayette

Hamza Khan

University of Oulu

Cristina Perfecto

University of the Basque Country

Antti Koskela

University of Oulu

Hamza Khan

Laurentian University

Tejas Kulkarni

National Institute of Technology Rourkela

Cooperative Institutions

University of Oulu

Purdue University West Lafayette

King Abdullah University of Science and Technology

Telefonica Research and Development

Nokia (Finland)

Cairo University

Catalyse

Unité de catalyse et de chimie du solide de Lille

Kyung Hee University

Seoul National University of Science and Technology

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

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

arXiv (Cornell University) (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. Standard SL algorithms assume an ideal underlying digital communication system and ignore the problem of scarce communication bandwidth. However, for a large number of agents, limited bandwidth resources, and time-varying communication channels, the communication bandwidth can become the bottleneck. To address this challenge, in this work, we propose a novel SL framework to solve the remote inference problem that introduces an additional layer at the agent side and constrains the choices of the weights and the biases to ensure over the air aggregation. Hence, the proposed approach maintains constant communication cost with respect to the number of agents enabling remote inference under limited bandwidth. Numerical results show that our proposed algorithm significantly outperforms the digital implementation in terms of communication-efficiency, especially as the number of agents grows large.

Popularity

10.48550/arxiv.2106.00999

Cite

Citations (0)

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

2015 IEEE Global Communications Conference (GLOBECOM) (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. Standard SL algorithms assume an ideal underlying digital communication system and ignore the problem of scarce communication bandwidth. However, for a large number of agents, limited bandwidth resources, and time-varying commu-nication channels, the communication bandwidth can become the bottleneck. To address this challenge, in this work, we propose a novel SL framework to solve the remote inference problem that introduces an additional layer at the agent side and constrains the choices of the weights and the biases to ensure over the air aggregation. Hence, the proposed approach maintains constant communication cost with respect to the number of agents enabling remote inference under limited bandwidth. Numerical results show that our proposed algorithm significantly outper-forms the digital implementation in terms of communication-efficiency" especially as the number of agents grows large.

10.1109/globecom46510.2021.9685045

Cite

Citations (16)

Communication Efficient Differentially Private Federated Learning Using Second Order Information

Proceedings on Privacy Enhancing Technologies (2024)

Mounssif Krouka Antti Koskela Tejas Kulkarni

Training machine learning models with differential privacy (DP) is commonly done using first-order methods such as DP-SGD. In the non-private setting, second-order methods try to mitigate the slow convergence of first-order methods. The DP methods that use second-order information still provide faster convergence, however the existing methods cannot be easily turned into federated learning (FL) algorithms without an excessive communication cost required by the exchange of the Hessian or feature covariance information between the nodes and the server. In this paper we propose DP-FedNew, a DP method for FL that uses second-order information and results in per-iteration communication cost similar to first-order methods such as DP Federated Averaging.

10.56553/popets-2025-0032

Cite

Citations (0)

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

arXiv (Cornell University) (2021)

Mounssif Krouka Anis Elgabli Chaouki Ben Issaid Mehdi Bennis

Today's intelligent applications can achieve high performance accuracy using machine learning (ML) techniques, such as deep neural networks (DNNs). Traditionally, in a remote DNN inference problem, an edge device transmits raw data to a remote node that performs the inference task. However, this may incur high transmission energy costs and puts data privacy at risk. 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. The time-varying representation accounts for time-varying channels and can significantly reduce the total energy at the edge device while maintaining high accuracy (low loss). We implement our approach in an image classification task using the MNIST dataset, and the system environment is simulated as a trajectory navigation scenario to emulate different channel conditions. Numerical simulations show that our proposed solution results in minimal energy consumption and $CO_2$ emission compared to the considered baselines while exhibiting robust performance across different channel conditions and bandwidth regime choices.

MNIST database

Edge device

Source

Cite

Citations (1)

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

Mounssif Krouka Anis Elgabli Chaouki Ben Issaid Mehdi Bennis

Today's intelligent applications can achieve high performance accuracy using machine learning (ML) techniques, such as deep neural networks (DNNs). Traditionally, in a remote DNN inference problem, an edge device transmits raw data to a remote node that performs the inference task. However, this may incur high transmission energy costs and puts data privacy at risk. 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. The time-varying representation accounts for time-varying channels and can significantly reduce the total energy at the edge device while maintaining high accuracy (low loss). We implement our approach in an image classification task using the MNIST dataset, and the system environment is simulated as a trajectory navigation scenario to emulate different channel conditions. Numerical simulations show that our proposed solution results in minimal energy consumption and CO 2 emission compared to the considered baselines while exhibiting robust performance across different channel conditions and bandwidth regime choices.

MNIST database

10.1109/pimrc50174.2021.9569707

Cite

Citations (12)

Communication-Efficient Second-Order Newton-Type Approach for Decentralized Learning

2022 IEEE Wireless Communications and Networking Conference (WCNC) (2023)

Mounssif Krouka Anis Elgabli Chaouki Ben Issaid Mehdi Bennis

In this paper, we propose a decentralized Newton-type approach to solve the problem of decentralized federated learning (FL). Notably, our proposed algorithm leverages the fast convergence of the second-order methods while avoid sending the hessian matrix at each iteration. Therefore, the proposed approach significantly reduces the communication cost and preserves the privacy. Specifically, we alternate between two problems. The inner problem approximates the inverse Hessian-gradient product which is formulated as a quadratic optimization problem and approximately solved in a decentralized manner using one step of the group alternating direction method of multipliers (GADMM) method. The outer problem learns the model, which is solved by performing one decentralized Newton step at every iteration. Moreover, to reduce the communication-overhead per iteration, a quantized version (leveraging stochastic quantization) is also proposed. Simulation results illustrate that our algorithm outperforms the baselines of GADMM, Q-GADMM, Newton tracking, and Decentralized SGD, and provides energy and communication-efficient solutions for bandwidth-limited systems under different SNR regimes.

Hessian matrix

10.1109/wcnc55385.2023.10118646

Cite

Citations (0)

Communication-Efficient Federated Learning: A Second Order Newton-Type Method With Analog Over-the-Air Aggregation

IEEE Transactions on Green Communications and Networking (2022)

Mounssif Krouka Anis Elgabli Chaouki Ben Issaid Mehdi Bennis

Owing to their fast convergence, second-order Newton-type learning methods have recently received attention in the federated learning (FL) setting. However, current solutions are based on communicating the Hessian matrices from the devices to the parameter server, at every iteration, incurring a large number of communication rounds; calling for novel communication-efficient Newton-type learning methods. In this article, we propose a novel second-order Newton-type method that, similarly to its first-order counterpart, requires every device to share only a model-sized vector at each iteration while hiding the gradient and Hessian information. In doing so, the proposed approach is significantly more communication-efficient and privacy-preserving. Furthermore, by leveraging the over-the-air aggregation principle, our method inherits privacy guarantees and obtains much higher communication efficiency gains. In particular, we formulate the problem of learning the inverse Hessian-gradient product as a quadratic problem that is solved in a distributed way. The framework alternates between updating the inverse Hessian-gradient product using a few alternating direction method of multipliers (ADMM) steps, and updating the global model using Newton's method. Numerical results show that our proposed approach is more communication-efficient and scalable under noisy channels for different scenarios and across multiple datasets.

Hessian matrix

10.1109/tgcn.2022.3173420

Cite

Citations (9)

Maximum Allowable Transfer Interval Aware Scheduling for Wireless Remote Monitoring

2022 IEEE Wireless Communications and Networking Conference (WCNC) (2020)

Mounssif Krouka Anis Elgabli Mehdi Bennis

In this paper, we tackle the problem of remote monitoring (e.g., remote factory) in which a number of sensor nodes are transmitting time sensitive measurements to a remote monitoring site. We assume that packets generated by different sensors have different sizes. Moreover, different sensors have different Maximum Allowable Transfer Intervals (MATIs). We consider minimizing a metric that maintains a trade-off between minimizing the average MATI violation of all sensors, and minimizing the probability that the MATI violation of each sensor exceeds a predefined threshold. We formulate the problem as a stochastic optimization problem with integer constraints. In order to solve this problem, we first relax the original intractable formulation to a tractable problem. Then, we use the Lyapunov stochastic optimization framework to solve the relaxed problem. Simulation results show that the proposed algorithm outperforms the considered baselines in terms of minimizing the probability of the MATI violation for all sensors.

Lyapunov optimization

10.1109/wcnc45663.2020.9120636

Cite

Citations (1)

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

arXiv (Cornell University) (2020)

Mounssif Krouka Anis Elgabli Mohammed S. Elbamby Cristina Perfecto Mehdi Bennis

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.

Cross-Layer Optimization

Degree (music)

Video Streaming

10.48550/arxiv.2011.06356

Cite

Citations (3)

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

Anis Elgabli Mohammed S. Elbamby Cristina Perfecto Mounssif Krouka Mehdi Bennis

Cross-Layer Optimization

Streaming current

Video Streaming

10.1109/mass62177.2024.00013

Cite

Citations (0)