From Graph Generation to Graph Classification

TL;DR

This paper introduces a novel graph classification method using generative models, deriving new formulas and training techniques for improved discrimination in graph data.

Contribution

It presents a new approach to graph classification leveraging generative models and derives classification formulas based on joint probability distributions.

Findings

Derives classification formulas for graphs using GGM.

Introduces a conditional ELBO for training graph auto-encoders.

Proposes a novel generative approach to graph classification.

Abstract

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.