GitHub

Data-Centric Learning from Unlabeled Graphs with Diffusion Model

This is the code for DCT, a data-centric transfer learning framework with diffusion model on graphs. This data-centric approach avoids the inappropriate designs of hand-crafted self-supervised tasks ...
Frontiers

Assessing the impact of disabilities on healthcare access among Sudanese refugees in Egypt during the 2023 crisis: a discriminant analysis approach

Introduction: The longstanding presence of Sudanese refugees in Egypt—fueled by decades of political instability, conflict, and economic hardship in Sudan—has evolved with the recent 2023 crisis. This ...
IEEE

A Comprehensive Survey on Graph Summarization With Graph Neural Networks

Abstract: As large-scale graphs become more widespread, more and more computational challenges with extracting, processing, and interpreting large graph data are being exposed. It is therefore natural ...
IEEE

Permutation Equivariant Graph Framelets for Heterophilous Graph Learning

Abstract: The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network (GNN) models and suggests aggregations ...