arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.07989cs.LGstat.ML
收藏

从图生成到图分类

From Graph Generation to Graph Classification

School of Computing Science(计算科学学院);Simon Fraser University(西蒙弗雷泽大学)

Oliver Schulte

AI总结:

本研究提出一种利用图生成模型(GGM)的图分类新方法,推导了对应分类公式,提出用条件ELBO训练生成式图自编码器用于判别,为图分类领域提供了新思路。

摘要:

本说明介绍了一种利用图生成模型(GGM)进行图分类的新方法。假设存在一个定义了图及其类别标签联合概率分布的图生成模型(GGM),本文推导了给定图时类别标签概率的分类公式。一种新的条件证据下界(ELBO)可用于训练用于判别的生成式图自编码器模型。虽然利用生成模型进行分类在非关系型独立同分布(i.i.d.)数据上已得到充分探索,但据我们所知,这是一种新颖的图分类方法。

英文摘要:

This note describes a new approach to classifying graphs that leverages graph generative models (GGM). Assuming a GGM that defines a joint probability distribution over graphs and their class labels, I derive classification formulas for the probability of a class label given a graph. A new conditional ELBO can be used to train a generative graph auto-encoder model for discrimination. While leveraging generative models for classification has been well explored for non-relational i.i.d. data, to our knowledge it is a novel approach to graph classification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑