论文标题
G-Mixup：图形分类的图形数据增强
G-Mixup: Graph Data Augmentation for Graph Classification
论文作者
论文摘要
这项工作开发了\ emph {混合图数据}。混合通过在两个随机样本之间插值特征和标签来改善神经网络的概括和鲁棒性表现出了优势。传统上，混合可以在常规，网格状和欧几里得数据（例如图像或表格数据）上工作。但是，直接采用混音来增强图形数据是一项挑战，因为通常不同的图：1）具有不同数量的节点。 2）不容易对齐； 3）在非欧几里得空间中具有独特的类型。为此，我们建议$ \ MATHCAL {G} $ - 混合以增强图形分类，以通过对不同类图的生成器（即Graphon）进行插值。具体而言，我们首先在同一类中使用图表来估计图形。然后，我们没有直接操纵图形，而是在欧几里得空间中的不同类别插值图形以获取混合图形，其中合成图是通过基于混合图形的采样生成的。广泛的实验表明，$ \ MATHCAL {G} $ - 混合可大大提高GNN的概括和稳健性。
This work develops \emph{mixup for graph data}. Mixup has shown superiority in improving the generalization and robustness of neural networks by interpolating features and labels between two random samples. Traditionally, Mixup can work on regular, grid-like, and Euclidean data such as image or tabular data. However, it is challenging to directly adopt Mixup to augment graph data because different graphs typically: 1) have different numbers of nodes; 2) are not readily aligned; and 3) have unique typologies in non-Euclidean space. To this end, we propose $\mathcal{G}$-Mixup to augment graphs for graph classification by interpolating the generator (i.e., graphon) of different classes of graphs. Specifically, we first use graphs within the same class to estimate a graphon. Then, instead of directly manipulating graphs, we interpolate graphons of different classes in the Euclidean space to get mixed graphons, where the synthetic graphs are generated through sampling based on the mixed graphons. Extensive experiments show that $\mathcal{G}$-Mixup substantially improves the generalization and robustness of GNNs.
