Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing
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.
Code (1)
Tasks
General ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The Infinite Contextual Graph Markov Model
The Contextual Graph Markov Model is a deep, unsupervised, and probabilistic model for graphs that is trained incrementally on a layer-by-layer basis. As with most Deep Graph Networks, an inherent limitation is the lack …
Graph ClassificationmodelModel SelectionModeling Edge Features with Deep Bayesian Graph Networks
We propose an extension of the Contextual Graph Markov Model, a deep and probabilistic machine learning model for graphs, to model the distribution of edge features. Our approach is architectural, as we introduce an addi…
Graph ClassificationGraph RegressionLink PredictionSHADOWCAST: Controllable Graph Generation
We introduce the controllable graph generation problem, formulated as controlling graph attributes during the generative process to produce desired graphs with understandable structures. Using a transparent and straightf…
Generative Adversarial NetworkGraph GenerationStructure Learning of Contextual Markov Networks using Marginal Pseudo-likelihood
Markov networks are popular models for discrete multivariate systems where the dependence structure of the variables is specified by an undirected graph. To allow for more expressive dependence structures, several genera…
Extracting Paragraphs from LLM Token Activations
Generative large language models (LLMs) excel in natural language processing tasks, yet their inner workings remain underexplored beyond token-level predictions. This study investigates the degree to which these models d…