Yang Zhi, Yan Yadong, Gan Haitao, Zhao Jing, Ye Zhiwei
School of Computer Science, Hubei University of Technology, Wuhan 430068, China.
State Key Laboratory of Biocatalysis and Enzyme Engineering, School of Life Sciences, Hubei University, Wuhan 430062, China.
Math Biosci Eng. 2022 Aug 31;19(12):12677-12692. doi: 10.3934/mbe.2022592.
In the semi-supervised learning field, Graph Convolution Network (GCN), as a variant model of GNN, has achieved promising results for non-Euclidean data by introducing convolution into GNN. However, GCN and its variant models fail to safely use the information of risk unlabeled data, which will degrade the performance of semi-supervised learning. Therefore, we propose a Safe GCN framework (Safe-GCN) to improve the learning performance. In the Safe-GCN, we design an iterative process to label the unlabeled data. In each iteration, a GCN and its supervised version (S-GCN) are learned to find the unlabeled data with high confidence. The high-confidence unlabeled data and their pseudo labels are then added to the label set. Finally, both added unlabeled data and labeled ones are used to train a S-GCN which can achieve the safe exploration of the risk unlabeled data and enable safe use of large numbers of unlabeled data. The performance of Safe-GCN is evaluated on three well-known citation network datasets and the obtained results demonstrate the effectiveness of the proposed framework over several graph-based semi-supervised learning methods.
在半监督学习领域，图卷积网络（GCN）作为图神经网络（GNN）的一种变体模型，通过将卷积引入GNN，在非欧几里得数据方面取得了不错的成果。然而，GCN及其变体模型未能安全地利用风险未标记数据的信息，这会降低半监督学习的性能。因此，我们提出了一种安全GCN框架（Safe-GCN）来提高学习性能。在Safe-GCN中，我们设计了一个迭代过程来标记未标记数据。在每次迭代中，学习一个GCN及其监督版本（S-GCN），以找到具有高置信度的未标记数据。然后将高置信度的未标记数据及其伪标签添加到标签集中。最后，使用添加的未标记数据和已标记数据来训练一个S-GCN，该S-GCN可以实现对风险未标记数据的安全探索，并能够安全地使用大量未标记数据。在三个著名的引文网络数据集上评估了Safe-GCN的性能，所得结果证明了所提出的框架相对于几种基于图的半监督学习方法的有效性。
