Paper accepted at ICML 2022

The Infinite Contextual Graph Markov Model

After a year of hard work, rejections, good feedback, paper rewriting, and additional experiments, our Infinite Contextual Graph Markov Model has been accepted at ICML 2022!

iCGMM combines graph learning and Bayesian nonparametric to build a deep model that can decide the complexity of each of its layers and automatize the choice of its hyper-parameters during training.

Needless to say, this work wouldn’t have been possible without the incredible expertise of Daniele Castellana about BNP methods and the supervision of Davide Bacciu and Alessio Micheli. Kudos to this incredible team!

If you don’t want to wait for the proceedings, please consider taking a look at Section 4.3 of my PhD thesis (link at the top of the homepage).

Federico Errica
Federico Errica
PhD in Computer Science