Intent Profiling and Translation Through Emergent Communication

no code implementations • 5 Feb 2024 • Salwa Mostafa, Mohammed S. Elbamby, Mohamed K. Abdel-Aziz, Mehdi Bennis

Instead, a framework based on emergent communication is proposed for intent profiling, in which applications express their abstract quality-of-experience (QoE) intents to the network through emergent communication messages.

Self-Learning Translation

Vehicular Cooperative Perception Through Action Branching and Federated Reinforcement Learning

no code implementations • 7 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)

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

no code implementations • 27 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