From Graph Diffusion to Graph Classification

Jia Jun Cheng Xian, Sadegh Mahdavi, Renjie Liao, Oliver Schulte

Keywords: graph neural networks, graph classification, diffusion model, graph generative model

TL;DR: We propose a training and inference framework for training a graph diffusion generative classifier

Abstract:

Generative models have achieved remarkable success in state-of-the-art image and text tasks. Recently, score-based diffusion models have extended their success beyond image generation, showing competitive performance with discriminative methods in image classification tasks (Zimmermann et al., 2021). However, their application to classification in the graph domain, which presents unique challenges such as complex topologies, remains underexplored. We show how graph diffusion models can be applied for graph classification. We find that to achieve competitive classification accuracy, score-based graph diffusion models should be trained with a novel training objective tailored for graph classification.

Submission Number: 116