Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing
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.
Cite
Text
Bacciu et al. "Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing." International Conference on Machine Learning, 2018.Markdown
[Bacciu et al. "Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing." International Conference on Machine Learning, 2018.](https://mlanthology.org/icml/2018/bacciu2018icml-contextual/)BibTeX
@inproceedings{bacciu2018icml-contextual,
title = {{Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing}},
author = {Bacciu, Davide and Errica, Federico and Micheli, Alessio},
booktitle = {International Conference on Machine Learning},
year = {2018},
pages = {294-303},
volume = {80},
url = {https://mlanthology.org/icml/2018/bacciu2018icml-contextual/}
}