3 citations · 8 across the 14 of their papers we have counts for
8 papers · 1 filter
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…
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…
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…
Stochastic Subgraph Neighborhood Pooling for Subgraph Classification
Shweta Ann Jacob, Paul Louis, Amirali Salehi-Abari
Subgraph classification is an emerging field in graph representation learning where the task is to classify a group of nodes (i.e., a subgraph) within a graph. Subgraph classificat…
Simplifying Subgraph Representation Learning for Scalable Link Prediction
Paul Louis, Shweta Ann Jacob, Amirali Salehi-Abari
Link prediction on graphs is a fundamental problem. Subgraph representation learning approaches (SGRLs), by transforming link prediction to graph classification on the subgraphs ar…
Sampling Enclosing Subgraphs for Link Prediction
Paul Louis, Shweta Ann Jacob, Amirali Salehi-Abari
Link prediction is a fundamental problem for graph-structured data (e.g., social networks, drug side-effect networks, etc.). Graph neural networks have offered robust solutions for…
Distilling Knowledge via Intermediate Classifiers
Aryan Asadian, Amirali Salehi-Abari
The crux of knowledge distillation is to effectively train a resource-limited student model with the guide of a pre-trained larger teacher model. However, when there is a large dif…
Joint Variational Autoencoders for Recommendation with Implicit Feedback
Bahare Askari, Jaroslaw Szlichta, Amirali Salehi-Abari
Variational Autoencoders (VAEs) have recently shown promising performance in collaborative filtering with implicit feedback. These existing recommendation models learn user represe…