{
  "id": "2302.07989",
  "version": "v1",
  "published": "2023-02-15T23:18:47.000Z",
  "updated": "2023-02-15T23:18:47.000Z",
  "title": "From Graph Generation to Graph Classification",
  "authors": [
    "Oliver Schulte"
  ],
  "comment": "I welcome suggestions, comments, and proposals for collaboration to develop further the ideas in this paper. Please email oschulte@cs.sfu.ca. I am grateful to Renjie Liao for helpful comments",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-02-15T23:18:47.000Z"
    }
  ],
  "analyses": {
    "subjects": [
      "I.2.6"
    ],
    "keywords": [
      "graph classification",
      "graph generation",
      "class label",
      "generative graph auto-encoder model",
      "joint probability distribution"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}