Graph generation and probabilistic methods

Abstract

This short lecture will present three different approaches to graph generation from the ML literature, using a variety of techniques based on deep learning and probabilistic building blocks. We will then cover the motivation for incorporating uncertainty when making predictions and briefly discuss a novel approach to learning graph representations that achieves this.

Dr Cătălina Cangea

Senior Research Scientist

Senior Research Scientist at Google DeepMind, with a PhD in ML from the University of Cambridge, and inhaler of music :) Focus on generative music models, finding signals in data and human evaluation. Motivated by contributing ML-based knowledge and improvements to real-world systems!