
The author introduces Control-based Graph Contrastive Learning (CGCL) as a novel framework for unsupervised graph representation learning, leveraging graph controllability properties and advanced edge augmentation methods to create augmented data for contrastive learning while preserving the controllability rank of graphs.


coremsg

control-based-graph-embeddings-with-data-augmentation-for-contrastive-learning


Control-based Graph Embeddings with Data Augmentation for Contrastive Learning
