论文标题
基于分区的图形神经网络的主动学习
Partition-Based Active Learning for Graph Neural Networks
论文作者
论文摘要
我们在主动学习设置中使用图神经网络（GNN）研究了半监督学习的问题。我们提出了GraphPart，这是一种基于分区的新型主动学习方法。 GraphPart首先将图形分配到不相交的分区中，然后选择每个分区中的代表节点以查询。提出的方法是通过对图和节点特征上实际平滑度假设下的分类误差进行的新颖分析来激励的。在多个基准数据集上进行的广泛实验表明，在广泛的注释预算约束下，所提出的方法优于GNN的现有活跃学习方法。此外，所提出的方法不会引入其他超参数，这对于模型训练至关重要，尤其是在可能无法使用标记的验证集的主动学习环境中。
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.
