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.
翻译:我们在一个积极的学习结构中研究与图形神经网络(GNNs)进行半监督学习的问题。我们提议了图形部分,这是一个针对GNS的基于分区的新的积极学习方法。图部分首先将图形分割成不相连的分区,然后在每个分区内选择有代表性的节点进行查询。拟议方法的动机是,根据对图形和节点特点的现实平稳假设对分类错误进行新颖的分析。关于多个基准数据集的广泛实验表明,拟议的方法在广泛的注解预算限制下,优于GNNs的现有积极学习方法。此外,拟议方法没有引入额外的超参数,这对于模型培训至关重要,特别是在可能没有标签验证装置的积极学习环境中。