Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation

arXiv:2402.10468v1 Announce Type: new
Abstract: Graph contrastive learning (GCL) has emerged as a pivotal technique in the domain of graph representation learning. A crucial aspect of effective GCL is the caliber of generated positive and negative samples, which is intrinsically dictated by their resemblance to the original data. Nevertheless, precise control over similarity during sample generation presents a formidable challenge, often impeding the effective discovery of representative graph patterns. To address this challenge, we propose an innovative framework: Adversarial Curriculum …

abstract adversarial arxiv augmentation control cs.ai cs.lg curriculum data domain generated graph graph representation negative pivotal positive representation representation learning samples type wise