Tag: graph contrastive learning

Researchers introduced OTGCL, an optimal transport augmentation framework that preserves node-level degree structure during graph contrastive learning.

Researchers report a graph contrastive learning framework called COIN that combines continuous orthogonal augmentation with an information-balancing training principle and ...

A new spatially aware graph-learning framework called PlantCCC prioritizes context-specific ligand–receptor communication patterns in plant spatial transcriptomics.