Learning Augmentation for GNNs with Consistency Regularization

Hyeonjin Park, Seunghun Lee, Dasol Hwang, Jisu Jeong, Kyung Min Kim, Jung Woo Ha, Hyunwoo J. Kim

Research output: Contribution to journalArticlepeer-review


Graph neural networks (GNNs) have demonstrated superior performance in various tasks on graphs. However, existing GNNs often suffer from weak-generalization due to sparsely labeled datasets. Here we propose a novel framework that learns to augment the input features using topological information and automatically controls the strength of augmentation. Our framework learns the augmentor to minimize GNNs' loss on unseen labeled data while maximizing the consistency of GNNs' predictions on unlabeled data. This can be formulated as a meta-learning problem and our framework alternately optimizes the augmentor and GNNs for a target task. Our extensive experiments demonstrate that the proposed framework is applicable to any GNNs and significantly improves the performance of graph neural networks on node classification. In particular, our method provides 5.78% improvement with Graph convolutional network (GCN) on average across five benchmark datasets.

Original languageEnglish
Pages (from-to)127961-127972
Number of pages12
JournalIEEE Access
Publication statusPublished - 2021


  • Graph neural networks
  • augmentation
  • meta-learning
  • semi-supervised learning

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)
  • Electrical and Electronic Engineering


Dive into the research topics of 'Learning Augmentation for GNNs with Consistency Regularization'. Together they form a unique fingerprint.

Cite this