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

Davide Bacciu, Federico Errica, Alessio Micheli
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:294-303, 2018.

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 this Paper


BibTeX
@InProceedings{pmlr-v80-bacciu18a, title = {Contextual Graph {M}arkov Model: A Deep and Generative Approach to Graph Processing}, author = {Bacciu, Davide and Errica, Federico and Micheli, Alessio}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {294--303}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/bacciu18a/bacciu18a.pdf}, url = {https://proceedings.mlr.press/v80/bacciu18a.html}, 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.} }
Endnote
%0 Conference Paper %T Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing %A Davide Bacciu %A Federico Errica %A Alessio Micheli %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-bacciu18a %I PMLR %P 294--303 %U https://proceedings.mlr.press/v80/bacciu18a.html %V 80 %X 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.
APA
Bacciu, D., Errica, F. & Micheli, A.. (2018). Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:294-303 Available from https://proceedings.mlr.press/v80/bacciu18a.html.

Related Material