Graph Contrastive Learning with Personalized Augmentation

Graph contrastive learning (GCL) has emerged as an effective tool to learn representations for whole graphs in the absence of labels. The key idea is to maximize the agreement between two augmented views of each graph via data augmentation. Existing GCL models mainly focus on applying identical augmentation strategies for all graphs within a given scenario. However, real-world graphs are often not monomorphic but abstractions of diverse natures. Even within the same scenario (e.g., macromolecules and online communities), different graphs might need diverse augmentations to perform effective GCL. Thus, blindly augmenting all graphs without considering their individual characteristics may undermine the performance of GCL arts. However, it is non-trivial to achieve personalized allocation for all graphs since the search space is exponential to the number of graphs. To bridge the gap, we propose the first principled framework, termed as Graph contrastive learning with Personalized Augmentation (GPA). It advances conventional GCL by allowing each graph to choose its own suitable augmentation operations. To cope with the huge search space, we design a tailored augmentation selector by converting the discrete space into a continuous one, which is a plug-and-play module and can be effectively trained with downstream GCL models end to end. Extensive experiments across 10 benchmark datasets demonstrate the superiority of GPA against state-of-the-art competitors. Moreover, by visualizing the learned augmentation distributions across different types of datasets, we show that GPA can effectively identify the most suitable augmentations for each graph based on its characteristics.