English

Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing

Machine Learning 2019-11-26 v2 Artificial Intelligence Neural and Evolutionary Computing Machine Learning

Abstract

We introduce the Contextual Graph Markov Model, an approach combining ideas from generative models and neural networks for the processing of graph data. It founds on a constructive methodology to build a deep architecture comprising layers of probabilistic models that learn to encode the structured information in an incremental fashion. Context is diffused in an efficient and scalable way across the graph vertexes and edges. The resulting graph encoding is used in combination with discriminative models to address structure classification benchmarks.

Keywords

Cite

@article{arxiv.1805.10636,
  title  = {Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing},
  author = {Davide Bacciu and Federico Errica and Alessio Micheli},
  journal= {arXiv preprint arXiv:1805.10636},
  year   = {2019}
}
R2 v1 2026-06-23T02:09:40.196Z