13 papers
Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks
Mostafa Haghir Chehreghani
The paper shows that injecting independent Gaussian noise after each step of a recurrent graph neural network creates a stochastic dynamical system that remains diverse, proving ma…
Adaptive Long-term Embedding with Denoising and Augmentation for Recommendation
Zahra Akhlaghi, Mostafa Haghir Chehreghani
The rapid growth of the internet has made personalized recommendation systems indispensable. Graph-based sequential recommendation systems, powered by Graph Neural Networks (GNNs),…
AI Models for Depressive Disorder Detection and Diagnosis: A Review
Dorsa Macky Aleagha, Payam Zohari, Mostafa Haghir Chehreghani
Major Depressive Disorder is one of the leading causes of disability worldwide, yet its diagnosis still depends largely on subjective clinical assessments. Integrating Artificial I…
PBiLoss: Popularity-Aware Regularization to Improve Fairness in Graph-Based Recommender Systems
Mohammad Naeimi, Mostafa Haghir Chehreghani
Recommender systems based on graph neural networks (GNNs) have been proved to perform well on user-item interactions. However, they commonly suffer from popularity bias -- the tend…
Disentangling Popularity and Quality: An Edge Classification Approach for Fair Recommendation
Nemat Gholinejad, Mostafa Haghir Chehreghani
Graph neural networks (GNNs) have proven to be an effective tool for enhancing the performance of recommender systems. However, these systems often suffer from popularity bias, lea…
On the Complexity of Optimal Graph Rewiring for Oversmoothing and Oversquashing in Graph Neural Networks
Mostafa Haghir Chehreghani
Graph Neural Networks (GNNs) face two fundamental challenges when scaled to deep architectures: oversmoothing, where node representations converge to indistinguishable vectors, and…