Hello, and welcome to my home on the web! I’m Petar, a Senior Staff Research Scientist at Google DeepMind, Affiliated Lecturer at the University of Cambridge, and an Associate of Clare Hall, Cambridge. I hold a PhD in Computer Science from the University of Cambridge (Trinity College), obtained under the supervision of Pietro Liò. My research concerns aligning neural networks to (classical) computation, to assess and improve their out-of-distribution generalisation ability. Particularly, I focus on neural algorithmic reasoning (featured in VentureBeat), graph representation learning and categorical and geometric deep learning (a topic I’ve co-written a proto-book about). For my contributions, I am recognised as an ELLIS Scholar in the Geometric Deep Learning Program. I am the first author of Graph Attention Networks—a popular convolutional layer for graphs—and Deep Graph Infomax—a popular self-supervised learning pipeline for graphs (featured in ZDNet). My research has been used in substantially improving travel-time predictions in Google Maps (featured in Endgadget, VentureBeat, CNET, The Verge and ZDNet), guiding intuition of mathematicians towards new top-tier theorems and conjectures (featured in Nature, Science, Quanta Magazine, New Scientist, The Independent, Sky News, The Sunday Times, la Repubblica and The Conversation), the first full AI system for tactical suggestions in association football (featured in Financial Times, The Athletic, The Economist, New Scientist, Wired, MIT Technology Review, The Verge and El País), and the first AI-assisted top-percentile result in competitive programming.