Graph-structured datasets usually have irregular graph sizes and connectivities, rendering the use of recent data augmentation techniques, such as Mixup, difficult. To tackle this challenge, we present the first Mixup-like graph augmentation method at the graph-level called Graph Transplant, which mixes irregular graphs in data space. To be well defined on various scales of the graph, our method identifies the sub-structure as a mix unit that can preserve the local information. Since the mixup-based methods without special consideration of the context are prone to generate noisy samples, our method explicitly employs the node saliency information to select meaningful subgraphs and adaptively determine the labels. We extensively validate our method with diverse GNN architectures on multiple graph classification benchmark datasets from a wide range of graph domains of different sizes. Experimental results show the consistent superiority of our method over other basic data augmentation baselines. We also demonstrate that Graph Transplant enhances the performance in terms of robustness and model calibration.
翻译:图形结构数据集通常具有不规则的图形大小和连接性,使得很难使用最近的数据增强技术,例如混合式技术。为了应对这一挑战,我们在图形层面展示了第一种混合式图形增强方法,称为图形移植,在数据空间中混合非常规图形。在图表的不同尺度上,我们的方法将亚结构确定为一个组合单位,可以保存本地信息。由于不特别考虑背景的混合方法容易生成噪音样本,我们的方法明确使用节点信息来选择有意义的子集,并适应性地决定标签。我们在多个不同大小的图解分类基准数据集中以不同的图形图形分类结构对方法进行了广泛验证。实验结果显示,我们的方法与其他基本数据增强基线相比具有一贯的优势。我们还证明,“图移植”能够提高强度和模型校准的性能。