Graph Representation Learning under Uncertainty

Abstract

This talk will give an overview of our incoming NeurIPS submission. We present a framework for learning to represent graph-structured data under uncertainty and evaluate it on a series of existing and novel tasks. The latter include Cellular Automata and a subset of Cora-full for mixed-class and few-shot learning, whereas the existing data comes from geometric and biological domains.

Dr Cătălina Cangea

Quantitative Researcher

Quantitative researcher with 9 years of ML experience, most recently co-lead of Generative Music at Google DeepMind, with a PhD from the University of Cambridge, and inhaler of music :) Motivated by contributing ML-based knowledge and improvements to real-world systems!