Focus on informative graphs! Semi-supervised active learning for graph-level classification

doi:10.1016/j.patcog.2024.110567

Focus on informative graphs! Semi-supervised active learning for graph-level classification

2024-09-01

2

PRE

AI

DOI：10.1016/j.patcog.2024.110567

Original

Original request for help

Save

Abstract

En 中文

Graph-level classification is a critical problem in social analysis and bioinformatics. Since annotated labels are typically costly, we intend to study this challenging task in semi-supervised scenarios with limited budgets. Inspired by the fact that active learning is capable of interactively querying an oracle to annotate a small number of informative examples in the unlabeled dataset, we develop a novel Semi-supervised active learning framework termed GraphSpa for graph-level classification. To make the most of labeling budgets, we propose an effective unlabeled data selection strategy that takes both local similarity and global semantic structure into account. Specifically, we first construct an adaptive queue with labeled samples and select informative samples that have a low degree of similarity to the queue using the Min-Max principle from the local view. Further, we introduce class prototypes and select samples with a large predictive loss discrepancy from the global view. To harness the full potential of unlabeled data, we develop a semi-supervised active learning framework on the basis of our fusion selection strategy coupled with graph contrastive learning during active learning. The effectiveness of our GraphSpa is validated against state-of-the-art methods through experimental results on diverse real-world benchmark datasets.

Keywords:

Graph classification

Graph neural networks

Semi-supervised learning

Active learning

Focus on informative graphs! Semi-supervised active learning for graph-level classification

Abstract

Journal

Organization