“Reasoning Algorithmically: from Toy Experiments to AGI Modules”
Wednesday May 31, 2023 | Time 11:00-12:00 CEST
Inviting Professor: Pierre Vandergheynst
Hybrid: Room BM 5202
Neural networks that are able to reliably execute algorithmic computation may hold transformative potential to both machine learning and theoretical computer science. On one hand, they could enable the kind of extrapolative generalisation scarcely seen with deep learning models. On another, they may allow for running classical algorithms on inputs previously considered inaccessible to them.
Over the past few years, the pace of development in this area has gradually become intense. As someone who has been very active in its latest incarnation, I have witnessed these concepts grow from isolated ‘toy experiments’, through NeurIPS spotlights, all the way to helping detect patterns in complicated mathematical objects (published on the cover of Nature) and supporting the development of generalist reasoning agents.
In this talk, I will give my personal account of this journey, and especially how our own interpretation of this methodology, and understanding of its potential, changed with time. It should be of interest to a general audience interested in graphs, (classical) algorithms, reasoning, and building intelligent systems.
Petar is a Staff Research Scientist at DeepMind, an Affiliated Lecturer at the University of Cambridge, and an Associate of Clare Hall, Cambridge.
He holds a PhD in Computer Science from the University of Cambridge (Trinity College), obtained under the supervision of Pietro Liò. His research concerns geometric deep learning—devising neural network architectures that respect the invariances and symmetries in data (a topic he has co-written a proto-book about). For his contributions, he is recognised as an ELLIS Scholar in the Geometric Deep Learning Program. Particularly, he focuses on graph representation learning and its applications in algorithmic reasoning (featured in VentureBeat). He is 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). His research has been used in substantially improving travel-time predictions in Google Maps (featured in CNBC, Endgadget, VentureBeat, CNET, The Verge, and ZDNet), and 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).