论文标题
图形神经网络的测试时间培训
Test-Time Training for Graph Neural Networks
论文作者
论文摘要
图神经网络（GNN）在图形分类任务中取得了巨大进步。但是，经常注意到训练集和测试组之间的性能差距。为了弥合这样的差距，在这项工作中，我们介绍了GNN的第一个测试时间培训框架，以增强图形分类任务的模型概括能力。特别是，我们设计了一种新型的测试时间训练策略，其中使用自制学习，以调整每个测试图样本的GNN模型。基准数据集上的实验证明了所提出的框架的有效性，尤其是当训练集和测试集之间存在分布变化时。我们还进行了探索性研究和理论分析，以对拟议的图测试时间训练框架（GT3）设计的合理性有更深入的理解。
Graph Neural Networks (GNNs) have made tremendous progress in the graph classification task. However, a performance gap between the training set and the test set has often been noticed. To bridge such gap, in this work we introduce the first test-time training framework for GNNs to enhance the model generalization capacity for the graph classification task. In particular, we design a novel test-time training strategy with self-supervised learning to adjust the GNN model for each test graph sample. Experiments on the benchmark datasets have demonstrated the effectiveness of the proposed framework, especially when there are distribution shifts between training set and test set. We have also conducted exploratory studies and theoretical analysis to gain deeper understandings on the rationality of the design of the proposed graph test time training framework (GT3).
