activity
20182022
most citedExtreme URLLC: Vision, Challenges, and Key Enablers

104 citations · 150 across the 7 of their papers we have counts for

collaborators

21 papers

cs.LG20222 cited

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

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. By adding a…

cs.LG2021

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

Mounssif Krouka, Anis Elgabli, Chaouki ben Issaid +1

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

cs.LG2021

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

Mounssif Krouka, Anis Elgabli, Chaouki Ben Issaid +1

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 i…

cs.LG2021

Energy-Efficient and Federated Meta-Learning via Projected Stochastic Gradient Ascent

Anis Elgabli, Chaouki Ben Issaid, Amrit S. Bedi +2

In this paper, we propose an energy-efficient federated meta-learning framework. The objective is to enable learning a meta-model that can be fine-tuned to a new task with a few nu…

cs.LG2020

BayGo: Joint Bayesian Learning and Information-Aware Graph Optimization

Tamara Alshammari, Sumudu Samarakoon, Anis Elgabli +1

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 collaborati…

cs.LG2020

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

Chaouki Ben Issaid, Anis Elgabli, Jihong Park +2

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