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:我们研究了图神经网络在主动学习设置下的半监督学习问题。我们提出了GraphPart,一种划分基础的图神经网络主动学习方法。GraphPart 首先将图划分为不相交的分区,然后选择每个分区内代表节点进行查询。我们在实际光滑假设下对图和节点特征的分类误差进行了分析,从而提出了该方法。多个基准数据集的广泛实验表明,该方法在广泛的注释预算约束下优于现有图神经网络主动学习方法。此外,该方法不会引入额外的超参数,这对于模型训练来说非常重要,特别是在主动学习设置下,因为可能没有标记的验证集。