Xue-Yi Tan

GeoGRACE: Geometry-Inspired Low-Rank Parameter Perturbation for Efficient Graph Contrastive Learning

In molecular property prediction, unsupervised graph contrastive learning (GCL) is pivotal when obtaining labeled data is costly. However, conventional augmentation-free approaches based on parameter perturbation mainly rely on full-rank isotropic noise, which can introduce uncontrolled perturbations and impair semanti...