<ul><li>Self-supervised graph representation learning (SSGRL) is a representation learning paradigm used to reduce or avoid manual labeling.</li><li>Existing methods of graph data augmentation rely on heuristics and are effective only within specific application domains.</li><li>This study proposes a data-driven SSGRL approach that automatically learns graph augmentation from the graph's signal.</li><li>The proposed method outperforms baselines and performs similarly to semi-supervised methods in various experiments.</li></ul>

Data-Driven Self-Supervised Graph Representation Learning

Discover more