Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models

TL;DR

This paper introduces UniAug, a diffusion model-based universal graph structure augmentor that enhances data scaling and improves performance across diverse graph-based tasks by adaptively augmenting graph data.

Contribution

We develop UniAug, a novel diffusion model-based graph augmentor that enables effective data scaling across heterogeneous graphs for improved downstream task performance.

Findings

Consistent performance improvements across multiple graph tasks.

First demonstration of a cross-domain graph structure augmentor.

Effective adaptive augmentation via pre-trained diffusion models.

Abstract

Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This 'better with more' phenomenon enables the effectiveness of large-scale pre-training on vast amounts of data. However, current graph pre-training methods struggle to scale up data due to heterogeneity across graphs. To achieve effective data scaling, we aim to develop a general model that is able to capture diverse data patterns of graphs and can be utilized to adaptively help the downstream tasks. To this end, we propose UniAug, a universal graph structure augmentor built on a diffusion model. We first pre-train a discrete diffusion model on thousands of graphs across domains to learn the graph structural patterns. In the downstream phase, we provide adaptive enhancement by conducting graph structure augmentation with the help of the pre-trained diffusion model via guided generation. By leveraging the pre-trained diffusion model for structure augmentation, we consistently achieve performance improvements across various downstream tasks in a plug-and-play manner. To the best of our knowledge, this study represents the first demonstration of a data-scaling graph structure augmentor on graphs across domains.