From Graph Generation to Graph Classification
This addresses graph classification for researchers, but it is incremental as it adapts known generative classification methods to graphs.
The paper tackles graph classification by deriving classification formulas from graph generative models, resulting in a new conditional ELBO for training generative graph auto-encoders for discrimination.
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.