Graph data augmentation with Gromow-Wasserstein Barycenters

arXiv:2404.08376v1 Announce Type: new
Abstract: Graphs are ubiquitous in various fields, and deep learning methods have been successful applied in graph classification tasks. However, building large and diverse graph datasets for training can be expensive. While augmentation techniques exist for structured data like images or numerical data, the augmentation of graph data remains challenging. This is primarily due to the complex and non-Euclidean nature of graph data. In this paper, it has been proposed a novel augmentation strategy for graphs …

abstract arxiv augmentation building classification cs.ai cs.lg data datasets deep learning diverse fields graph graph data graphs however images numerical structured data tasks training type