Diego Mesquita

PhD student


I am a fourth-year PhD student at AaltoPML , supervised by Samuel Kaski. I am interested in Bayesian inference, deep learning and also the intersecetion of both. My recent work revolves around graph neural networks and Bayesian inference for distributed/multi-source data.

Follow me on twitter @wkly_infrmtive for somewhat regular updates and for occasional bad jokes. You can also contact me through first.last@aalto.fi


Selected Works

Rethinking pooling in graph neural networks

Diego Mesquita, Amauri Holanda and Samuel Kaski

[manuscript, code]

NeurIPS 2020

Embarrassingly parallel MCMC with deeep invertible transformations

Diego Mesquita, Paul Blomstedt and Samuel Kaski


UAI 2019

Meta-analysis of Bayesian analyses

Paul Blomstedt, Diego Mesquita, Jarno Lintusaari, Tuomas Sivula, Jukka Corander and Samuel Kaski



For a full list, have a look at my Google Scholar page.