Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing
This work addresses graph processing for machine learning applications, presenting a novel hybrid approach.
The paper tackles the problem of processing graph data by introducing the Contextual Graph Markov Model, which combines generative models and neural networks to encode structured information incrementally, achieving results on structure classification benchmarks.
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.