Data Augmentation for Deep Graph Learning: A Survey

TL;DR

This survey reviews various techniques for graph data augmentation, addressing challenges in deep graph learning related to data noise and scarcity, and categorizes applications in reliable and low-resource graph learning.

Contribution

It formally defines graph data augmentation, proposes a taxonomy, and systematically reviews techniques and applications in deep graph learning.

Findings

Categorizes graph data augmentation methods based on information modalities.

Highlights applications in reliable and low-resource graph learning.

Identifies future research directions and challenges.

Abstract

Graph neural networks, a powerful deep learning tool to model graph-structured data, have demonstrated remarkable performance on numerous graph learning tasks. To address the data noise and data scarcity issues in deep graph learning, the research on graph data augmentation has intensified lately. However, conventional data augmentation methods can hardly handle graph-structured data which is defined in non-Euclidean space with multi-modality. In this survey, we formally formulate the problem of graph data augmentation and further review the representative techniques and their applications in different deep graph learning problems. Specifically, we first propose a taxonomy for graph data augmentation techniques and then provide a structured review by categorizing the related work based on the augmented information modalities. Moreover, we summarize the applications of graph data augmentation in two representative problems in data-centric deep graph learning: (1) reliable graph learning which focuses on enhancing the utility of input graph as well as the model capacity via graph data augmentation; and (2) low-resource graph learning which targets on enlarging the labeled training data scale through graph data augmentation. For each problem, we also provide a hierarchical problem taxonomy and review the existing literature related to graph data augmentation. Finally, we point out promising research directions and the challenges in future research.