3 papers
cs.LG2025
GeoHNNs: Geometric Hamiltonian Neural Networks
Amine Mohamed Aboussalah, Abdessalam Ed-dib
The fundamental laws of physics are intrinsically geometric, dictating the evolution of systems through principles of symmetry and conservation. While modern machine learning offer…
stat.ML2025
Are GNNs doomed by the topology of their input graph?
Amine Mohamed Aboussalah, Abdessalam Ed-dib
Graph Neural Networks (GNNs) have demonstrated remarkable success in learning from graph-structured data. However, the influence of the input graph's topology on GNN behavior remai…
cs.LG2024
GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning
Abdessalam Ed-dib, Zhanibek Datbayev, Amine Mohamed Aboussalah
Fine-tuning large language models (LLMs) is computationally intensive because it requires updating all parameters. Low-Rank Adaptation (LoRA) improves efficiency by modifying only…