3 papers
cs.LG2026
RADE: Random Add-Drop Edge as a Regularizer
Danial Saber, Amirali Salehi-Abari
Graph Neural Networks (GNNs) suffer from overfitting and over-squashing of long-range information. Stochastic graph augmentations (e.g., edge deletion) regularize training against…
cs.LG2025
Over-Squashing in GNNs and Causal Inference of Rewiring Strategies
Danial Saber, Amirali Salehi-Abari
Graph neural networks (GNNs) have exhibited state-of-the-art performance across wide-range of domains such as recommender systems, material design, and drug repurposing. Yet messag…
cs.LG2024
Scalable Expressiveness through Preprocessed Graph Perturbations
Danial Saber, Amirali Salehi-Abari
Graph Neural Networks (GNNs) have emerged as the predominant method for analyzing graph-structured data. However, canonical GNNs have limited expressive power and generalization ca…