← Search

Daniele Castellana

2 accepted papers

2022

The Infinite Contextual Graph Markov Model

ICML 2022spotlight

The Contextual Graph Markov Model (CGMM) 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 need to perform an extensive model selection to choose the proper size of each…