Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs

TL;DR

This paper investigates the use of synthetic graph generation for data augmentation in Graph Neural Networks, demonstrating improved classification performance and discussing generator selection based on graph size.

Contribution

It introduces a novel approach to augment graph data with generated graphs, improving GNN performance while addressing challenges like data scarcity and quality control.

Findings

Generated graphs enhance classification accuracy.

Generator choice depends on graph size.

Balancing scalability and quality is crucial.

Abstract

Graphs are crucial for representing interrelated data and aiding predictive modeling by capturing complex relationships. Achieving high-quality graph representation is important for identifying linked patterns, leading to improvements in Graph Neural Networks (GNNs) to better capture data structures. However, challenges such as data scarcity, high collection costs, and ethical concerns limit progress. As a result, generative models and data augmentation have become more and more popular. This study explores using generated graphs for data augmentation, comparing the performance of combining generated graphs with real graphs, and examining the effect of different quantities of generated graphs on graph classification tasks. The experiments show that balancing scalability and quality requires different generators based on graph size. Our results introduce a new approach to graph data augmentation, ensuring consistent labels and enhancing classification performance.