AI RESEARCH

Adaptive Negative Scheduling for Graph Contrastive Learning

arXiv CS.LG

ArXi:2605.03076v1 Announce Type: new Graph contrastive learning (GCL) has become a central paradigm for self-supervised representation learning in computational intelligence, with applications spanning recommendation, anomaly detection, and personalization. A key limitation of existing methods is their reliance on static negative sampling, which fails to account for the dynamic informativeness and computational cost of negatives during