Search Results for author:
Found 2 papers, 1 papers with code
Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learning
We further propose Graph selective attention networks (SATs) to learn representations from the highly correlated node features identified and investigated by different SA mechanisms.
SCE: Scalable Network Embedding from Sparsest Cut
A key of success to such contrastive learning methods is how to draw positive and negative samples.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
