Skip to main content Skip to footer

Petar Veličković

College positions:
Computer Science
DeepMind, University of Cambridge
Contact details:

Dr Petar Veličković

Dr Petar Veličković is a Staff Research Scientist at DeepMind, and an Affiliated Lecturer at the University of Cambridge.

He holds a PhD in Computer Science from the University of Cambridge (Trinity College), obtained under the supervision of Professor Pietro Liò’, who is a Fellow of Clare Hall.

Dr Veličković’s research concerns geometric deep learning – devising neural network architectures that respect the invariances and symmetries in data (a topic on which he has co-written a proto-book about). He is recognised as an ELLIS Scholar in the Geometric Deep Learning Programme. In this area, Dr Veličković focuses on graph representation learning and its applications in algorithmic reasoning and computational biology. In particular, 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).

Used in substantially improving the travel-time predictions in Google Maps (featured in the CNBC, Endgadget, VentureBeat, CNET, The Verge and ZDNet), Dr Veličković’s research has also guided the 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 and The Conversation).

Select publications

  • Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges, MM. Bronstein, J. Bruna, T. Cohen and P. Veličković, arXiv preprint arXiv:2104.13478 (2021)
  • Advancing mathematics by guiding human intuition with AI, A. Davies, P. Veličković, L. Buesing, S. Blackwell, D. Zheng, N. Tomašev, R. Tanburn, P. Battaglia, C. Blundell, A. Juhász, M. Lackenby, G. Williamson, D. Hassabis and P. Kohli, Nature 600 (7887), 70-74 (2021)
  • ETA Prediction with Graph Neural Networks in Google Maps, A. Derrow-Pinion, J. She, D. Wong, O. Lange, T. Hester, L. Perez, M. Nunkesser, S. Lee, X. Guo, B. Wiltshire, PW. Battaglia, V. Gupta, A. Li, Z. Xu, A. Sanchez-Gonzalez, Y. Li and P. Veličković, The 30th ACM International Conference on Information & Knowledge Management (CIKM’21)
  • Graph Attention Networks, P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò and Y. Bengio, The 6th International Conference on Learning Representations (ICLR’18)
  • Deep Graph Infomax, P. Veličković, W. Fedus, WL. Hamilton, P. Liò, Y. Bengio and RD. Hjelm, The 7th International Conference on Learning Representations (ICLR’19)
  • Neural Execution of Graph Algorithms, P. Veličković, R. Ying, M. Padovano, R. Hadsell and C. Blundell, The 8th International Conference on Learning Representations (ICLR’20)
  • Neural Algorithmic Reasoners are Implicit Planners, A. Deac, P. Veličković, O. Milinković, PL. Bacon, J. Tang and M. Nikolić, The 34th International Conference on Advances in Neural Information Processing Systems (NeurIPS’21); Spotlight
  • The CLRS Algorithmic Reasoning Benchmark, P. Veličković, A. Puigdomènech Badia, D. Budden, R. Pascanu, A. Banino, M. Dashevskiy, R. Hadsell and C. Blundell, The 39th International Conference on Machine Learning (ICML’22)

Select awards

  • Wiseman Prize, Department of Computer Science and Technology, University of Cambridge, 2017
  • Senior Scholar, Trinity College, Cambridge, 2014

Further links