Overcoming Pitfalls in Graph Contrastive Learning Evaluation: Toward Comprehensive Benchmarks

arXiv:2402.15680v1 Announce Type: new
Abstract: The rise of self-supervised learning, which operates without the need for labeled data, has garnered significant interest within the graph learning community. This enthusiasm has led to the development of numerous Graph Contrastive Learning (GCL) techniques, all aiming to create a versatile graph encoder that leverages the wealth of unlabeled data for various downstream tasks. However, the current evaluation standards for GCL approaches are flawed due to the need for extensive hyper-parameter tuning during pre-training …

abstract arxiv benchmarks community cs.lg data development encoder evaluation graph graph learning self-supervised learning supervised learning type