collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

When does distribution shift break graph neural networks calibration?

Abderaouf Bahi

Graph neural networks (GNNs) are increasingly deployed in real-world applications where distribution shift is un-avoidable. However, how such shifts affect model calibration, defin…

cs.LG2026

Graph Neural Networks Applications Across Domains: All Insights You Need

Abderaouf Bahi

Graph neural networks have moved from a niche representation-learning technique to the default model class wherever data carry relational structure. The interesting question is no…

cs.LG2026

FreeGNN: Continual Source-Free Graph Neural Network Adaptation for Renewable Energy Forecasting

Abderaouf Bahi, Amel Ourici, Ibtissem Gasmi +3

Accurate forecasting of renewable energy generation is essential for efficient grid management and sustainable power planning. However, traditional supervised models often require…

cs.LG2025

GNN-ASE: Graph-Based Anomaly Detection and Severity Estimation in Three-Phase Induction Machines

Moutaz Bellah Bentrad, Adel Ghoggal, Tahar Bahi +1

The diagnosis of induction machines has traditionally relied on model-based methods that require the development of complex dynamic models, making them difficult to implement and c…

cs.LG2025

Green Energy Management for Sustainable Data Centers Using Deep Reinforcement Learning

Abderaouf Bahi, Amel Ourici, Hasan Dincer +2

The exponential growth of digital services has positioned data centers among the most energy-intensive infrastructures in the modern economy, raising critical concerns regarding op…