3 papers
cs.LG2026
Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs
Tanvir Hossain, Muhammad Ifte Khairul Islam, Lilia Chebbah +2
Graph neural networks (GNNs) have achieved strong performance across various real-world domains. Nevertheless, they suffer from oversquashing, where long-range information is disto…
cs.LG2024
Tackling Oversmoothing in GNN via Graph Sparsification: A Truss-based Approach
Tanvir Hossain, Khaled Mohammed Saifuddin, Muhammad Ifte Khairul Islam +2
Graph Neural Network (GNN) achieves great success for node-level and graph-level tasks via encoding meaningful topological structures of networks in various domains, ranging from s…
math.AT2023
Hypergraph Classification via Persistent Homology
Mehmet Emin Aktas, Thu Nguyen, Rakin Riza +2
Persistent homology is a mathematical tool used for studying the shape of data by extracting its topological features. It has gained popularity in network science due to its applic…