将扩散模型用于图分类，设计新训练目标提升性能。
From Graph Diffusion to Graph Classification
- 基于分数的图扩散模型，专为分类任务设计新训练目标。
- 采样推理下达到当前最优图分类准确率。
- 适合研究图神经网络与生成模型融合的学者。
生成模型如扩散模型在图像和文本任务中取得显著成功。近期，基于分数的扩散模型已扩展至图像分类任务，并展现出与判别式方法相当的性能。然而，在具有复杂拓扑结构的图领域中，其应用仍不充分。本文展示了如何将图扩散模型应用于图分类任务。研究发现，为实现竞争性分类精度，基于分数的图扩散模型需采用专为图分类设计的新训练目标。在使用采样推理方法的实验中，该判别式训练目标实现了最先进的图分类准确率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。