Partition-Based Active Learning for Graph Neural Networks

Jiaqi Ma, Ziqiao Ma, Joyce Chai, Qiaozhu Mei

Research output: Contribution to journalArticlepeer-review

Abstract

We study the problem of semi-supervised learning with Graph Neural Networks (GNNs) in an active learning setup. We propose GraphPart, a novel partition-based active learning approach for GNNs. GraphPart first splits the graph into disjoint partitions and then selects representative nodes within each partition to query. The proposed method is motivated by a novel analysis of the classification error under realistic smoothness assumptions over the graph and the node features. Extensive experiments on multiple benchmark datasets demonstrate that the proposed method outperforms existing active learning methods for GNNs under a wide range of annotation budget constraints. In addition, the proposed method does not introduce additional hyperparameters, which is crucial for model training, especially in the active learning setting where a labeled validation set may not be available.

Original languageEnglish (US)
JournalTransactions on Machine Learning Research
Volume2023-March
StatePublished - 2023

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Partition-Based Active Learning for Graph Neural Networks'. Together they form a unique fingerprint.

Cite this