ORCID Profile
0000-0002-2063-8437
Current Organisation
University of Sydney
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2019
Publisher: Springer Science and Business Media LLC
Date: 09-11-2022
DOI: 10.1007/S10618-022-00879-4
Abstract: Graph neural networks (GNNs) have achieved state-of-the-art results for semi-supervised node classification on graphs. Nevertheless, the challenge of how to effectively learn GNNs with very few labels is still under-explored. As one of the prevalent semi-supervised methods, pseudo-labeling has been proposed to explicitly address the label scarcity problem. It is the process of augmenting the training set with pseudo-labeled unlabeled nodes to retrain a model in a self-training cycle. However, the existing pseudo-labeling approaches often suffer from two major drawbacks. First, these methods conservatively expand the label set by selecting only high-confidence unlabeled nodes without assessing their informativeness. Second, these methods incorporate pseudo-labels to the same loss function with genuine labels, ignoring their distinct contributions to the classification task. In this paper, we propose a novel informative pseudo-labeling framework (InfoGNN) to facilitate learning of GNNs with very few labels. Our key idea is to pseudo-label the most informative nodes that can maximally represent the local neighborhoods via mutual information maximization. To mitigate the potential label noise and class-imbalance problem arising from pseudo-labeling, we also carefully devise a generalized cross entropy with a class-balanced regularization to incorporate pseudo-labels into model retraining. Extensive experiments on six real-world graph datasets validate that our proposed approach significantly outperforms state-of-the-art baselines and competitive self-supervised methods on graphs.
Location: Australia
No related grants have been discovered for Jie Yin.