I am an experienced research engineer with a background in wireless
communications, signal processing, and machine learning. I am currently a
Task leader in the SNS JU 6G Project "ADROIT6G". I collaborate with experts in academia and industry on
several research
projects focusing on the next generation of wireless systems (5G and beyond).
EU's Horizon Europe project "ADROIT6G": Disruptive
innovations in the architecture of emerging 6G mobile networks, that will make fundamental changes to the
way networks are designed, implemented, operated, and maintained
Research topic: Artificial Intelligence based CSI Feedback in massive MIMO
Contributed to the development of 5G and beyond physical layer modem systems.
Evaluated the use of Artificial Intelligence (AI)/Machine Learning (ML) methods for physical layer signal
processing in wireless communications.
Performed theoretical analysis and algorithm simulation.
Presented and documented the outputs of the research results.
(2017 - 2018) Centre for Wireless Communications (CWC), University of Oulu
Research Assistant
Research topics:
Spatial Multiplexing and Beamforming in 5G V2X Networks.
Initial Access in 5G mm-wave Cellular Networks: A Comparative Analysis using Hybrid Beamforming (Master
thesis work).
Latest Publications
Paper title:
Communication-Efficient Second-Order Newton-Type Approach
for
Decentralized Learning
Authors:
Mounssif Krouka, Anis Elgabli, Chaouki Ben Issaid, Mehdi Bennis
Abstract:
In this paper, we propose a decentralized Newtontype
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.
Plain Text: M. Krouka, A.
Elgabli, C. B. Issaid and M. Bennis, "Communication-Efficient Second-Order Newton-Type Approach
for Decentralized Learning," 2023 IEEE Wireless Communications and Networking Conference (WCNC),
Glasgow, United Kingdom, 2023, pp. 1-7, doi: 10.1109/WCNC55385.2023.10118646.
BibTeX:
@INPROCEEDINGS{10118646,
author={Krouka, Mounssif and Elgabli, Anis and Issaid, Chaouki Ben and Bennis, Mehdi},
booktitle={2023 IEEE Wireless Communications and Networking Conference (WCNC)},
title={Communication-Efficient Second-Order Newton-Type Approach for Decentralized Learning},
year={2023},
volume={},
number={},
pages={1-7},
doi={10.1109/WCNC55385.2023.10118646}}
Paper title:
Communication-Efficient Federated Learning: a Second Order
Newton-type Method
with
Analog Over-the-Air Aggregation
Authors:
Mounssif Krouka, Anis Elgabli, Chaouki Ben Issaid, Mehdi Bennis
Abstract:
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.
Plain Text: M. Krouka, A.
Elgabli, C. B. Issaid
and M. Bennis, "Communication-Efficient Federated Learning: A Second Order Newton-Type Method With
Analog
Over-the-Air Aggregation," in IEEE Transactions on Green Communications and Networking, vol. 6,
no. 3, pp.
1862-1874, Sept. 2022, doi: 10.1109/TGCN.2022.3173420.
BibTeX:
@ARTICLE{9770933,
author={Krouka, Mounssif and Elgabli, Anis and Issaid, Chaouki Ben and Bennis, Mehdi},
journal={IEEE Transactions on Green Communications and Networking},
title={Communication-Efficient Federated Learning: A Second Order Newton-Type Method With Analog
Over-the-Air
Aggregation},
year={2022},
volume={6},
number={3},
pages={1862-1874},
doi={10.1109/TGCN.2022.3173420}}
Paper title:
Communication-Efficient and Federated Multi-Agent
Reinforcement
Learning
Authors:
Mounssif Krouka, Anis Elgabli, Chaouki Ben Issaid, Mehdi Bennis
Abstract:
In this paper, we consider a distributed
reinforcement learning setting where ... agents
are communicating with a central entity in a shared environment to
maximize a global reward. A main challenge in this setting is that the randomness of the wireless
channel
perturbs
each agent’s model update while multiple agents’ updates may cause interference when communicating
under
limited
bandwidth. To address this issue, we propose a novel distributed reinforcement learning algorithm
based on
the
alternating direction method of multipliers (ADMM) and “ over air aggregation ” using analog
transmission
scheme,
referred to as A-RLADMM. Our algorithm incorporates the wireless channel into the formulation of
the
ADMM
method,
which enables agents to transmit each element of their updated models over the same channel using
analog
communication. Numerical experiments on a multi-agent collaborative navigation task show that our
proposed
algorithm
significantly outperforms the digital communication baseline of A-RLADMM (D-RLADMM), the lazily
aggregated
policy
gradient (RL-LAPG), as well as the analog and the digital communication versions of the vanilla
FL,
(A-FRL)
and
(D-FRL) respectively.
Plain Text: M. Krouka, A.
Elgabli, C. B. Issaid
and M. Bennis, "Communication-Efficient and Federated Multi-Agent Reinforcement Learning," in IEEE
Transactions on
Cognitive Communications and Networking, vol. 8, no. 1, pp. 311-320, March 2022, doi:
10.1109/TCCN.2021.3130993.
BibTeX:
@ARTICLE{9627728,
author={Krouka, Mounssif and Elgabli, Anis and Issaid, Chaouki Ben and Bennis, Mehdi},
journal={IEEE Transactions on Cognitive Communications and Networking},
title={Communication-Efficient and Federated Multi-Agent Reinforcement Learning},
year={2022},
volume={8},
number={1},
pages={311-320},
doi={10.1109/TCCN.2021.3130993}}
Paper title:
Communication-Efficient Split Learning Based on Analog
Communication
and Over the Air Aggregation
Authors:
Mounssif Krouka, Anis Elgabli, Chaouki Ben Issaid, Mehdi Bennis
Abstract:
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.
Plain Text: M. Krouka, A.
Elgabli, C. b. Issaid
and M. Bennis, "Communication-Efficient Split Learning Based on Analog Communication and Over the
Air Aggregation,"
2021 IEEE Global Communications Conference (GLOBECOM), Madrid, Spain, 2021, pp. 1-6, doi:
10.1109/GLOBECOM46510.2021.9685045.
BibTeX:
@INPROCEEDINGS{9685045,
author={Krouka, Mounssif and Elgabli, Anis and Issaid, Chaouki ben and Bennis, Mehdi},
booktitle={2021 IEEE Global Communications Conference (GLOBECOM)},
title={Communication-Efficient Split Learning Based on Analog Communication and Over the Air
Aggregation},
year={2021},
volume={},
number={},
pages={1-6},
doi={10.1109/GLOBECOM46510.2021.9685045}}
Paper title:
Energy-Efficient Model Compression and Splitting for
Collaborative
Inference Over Time-Varying Channels
Authors:
Mounssif Krouka, Anis Elgabli, Chaouki Ben Issaid, Mehdi Bennis
Abstract:
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.
Plain Text: M. Krouka, A.
Elgabli, C. B. Issaid
and M. Bennis, "Energy-Efficient Model Compression and Splitting for Collaborative Inference Over
Time-Varying
Channels," 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio
Communications
(PIMRC), Helsinki, Finland, 2021, pp. 1173-1178, doi: 10.1109/PIMRC50174.2021.9569707.
BibTeX:
@INPROCEEDINGS{9569707,
author={Krouka, Mounssif and Elgabli, Anis and Issaid, Chaouki Ben and Bennis, Mehdi},
booktitle={2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio
Communications
(PIMRC)},
title={Energy-Efficient Model Compression and Splitting for Collaborative Inference Over
Time-Varying Channels},
year={2021},
volume={},
number={},
pages={1173-1178},
doi={10.1109/PIMRC50174.2021.9569707}}
Paper title:
Maximum Allowable Transfer Interval Aware Scheduling for
Wireless
Remote Monitoring
Authors:
Mounssif Krouka, Anis Elgabli, Mehdi Bennis
Abstract:
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.
Plain Text: M. Krouka, A.
Elgabli and M. Bennis,
"Maximum Allowable Transfer Interval Aware Scheduling for Wireless Remote Monitoring," 2020 IEEE
Wireless
Communications and Networking Conference (WCNC), Seoul, Korea (South), 2020, pp. 1-6, doi:
10.1109/WCNC45663.2020.9120636.
BibTeX:
@INPROCEEDINGS{9120636,
author={Krouka, Mounssif and Elgabli, Anis and Bennis, Mehdi},
booktitle={2020 IEEE Wireless Communications and Networking Conference (WCNC)},
title={Maximum Allowable Transfer Interval Aware Scheduling for Wireless Remote Monitoring},
year={2020},
volume={},
number={},
pages={1-6},
doi={10.1109/WCNC45663.2020.9120636}}
Paper title:
Reinforcement Learning Based Scheduling Algorithm for
Optimizing Age
of Information in Ultra Reliable Low Latency Networks
Authors:
Anis Elgabli, Hamza Khan, Mounssif Krouka, Mehdi Bennis
Abstract:
Age of
Information (AoI) measures the freshness of the information ... Age of
Information (AoI) measures the freshness of the information at a remote location. AoI reflects the
time that
is
elapsed since the generation of the packet by a transmitter. In this paper, we consider a remote
monitoring
problem
(e.g., remote factory) in which a number of sensor nodes are transmitting time sensitive
measurements
to a
remote
monitoring site. We consider minimizing a metric that maintains a trade-off between minimizing the
sum
of
the expected
AoI of all sensors and minimizing an Ultra Reliable Low Latency Communication (URLLC) term. The
URLLC
term
is
considered to ensure that the probability the AoI of each sensor exceeds a predefined threshold is
minimized.
Moreover, we assume that sensors tolerate different threshold values and generate packets at
different
sizes.
Motivated by the success of machine learning in solving large networking problems at low
complexity,
we
develop a low
complexity reinforcement learning based algorithm to solve the proposed formulation. We trained
our
algorithm using
the state-of-the-art actor-critic algorithm over a set of public bandwidth traces. Simulation
results
show
that the
proposed algorithm outperforms the considered baselines in terms of minimizing the expected AoI
and
the
threshold
violation of each sensor.
Plain Text: A. Elgabli, H.
Khan, M. Krouka and M. Bennis, "Reinforcement Learning Based
Scheduling Algorithm for Optimizing Age of Information in Ultra Reliable Low Latency Networks,"
2019 IEEE Symposium on
Computers and Communications (ISCC), Barcelona, Spain, 2019, pp. 1-6, doi:
10.1109/ISCC47284.2019.8969641.
BibTeX:
@INPROCEEDINGS{8969641,
author={Elgabli, Anis and Khan, Hamza and Krouka, Mounssif and Bennis, Mehdi},
booktitle={2019 IEEE Symposium on Computers and Communications (ISCC)},
title={Reinforcement Learning Based Scheduling Algorithm for Optimizing Age of Information in
Ultra Reliable Low
Latency Networks},
year={2019},
volume={},
number={},
pages={1-6},
doi={10.1109/ISCC47284.2019.8969641}}