Oversmoothing: A Nightmare for Graph Contrastive Learning?

arXiv:2306.02117v2 Announce Type: replace
Abstract: Oversmoothing is a common phenomenon observed in graph neural networks (GNNs), in which an increase in the network depth leads to a deterioration in their performance. Graph contrastive learning (GCL) is emerging as a promising way of leveraging vast unlabeled graph data. As a marriage between GNNs and contrastive learning, it remains unclear whether GCL inherits the same oversmoothing defect from GNNs. This work undertakes a fundamental analysis of GCL from the perspective of oversmoothing …

abstract arxiv cs.ai cs.lg data gnns graph graph data graph neural networks leads marriage network networks neural networks performance type vast