From Graph Diffusion to Graph Classification
This work addresses graph classification, a domain-specific challenge with complex topologies, for researchers and practitioners in graph machine learning, representing an incremental advancement by adapting existing diffusion methods.
The paper tackles the problem of applying score-based diffusion models to graph classification by introducing a novel training objective tailored for this domain, achieving state-of-the-art accuracy in experiments.
Generative models such as diffusion 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 {\em classification} tasks~\cite{zimmermann2021score}. However, their application to classification in the {\em 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 that is tailored to graph classification. In experiments with a sampling-based inference method, our discriminative training objective achieves state-of-the-art graph classification accuracy.