skip to content

Department of Computer Science and Technology

  • Affiliated Lecturer
  • Associate, Clare Hall
  • Staff Research Scientist, DeepMind

I hold an Affiliated Lectureship at the University of Cambridge, where I am co-teaching an MPhil course on graph representation learning, and I am an Associate of Clare Hall, Cambridge. I am currently employed as a Staff Research Scientist at DeepMind. I hold a PhD in Computer Science from the University of Cambridge (Trinity College), obtained under the supervision of Pietro Liò.

My research concerns geometric deep learning—devising neural network architectures that respect the invariances and symmetries in data (a topic I’ve co-written a proto-book about). Within this area, I focus on graph representation learning and its applications in algorithmic reasoning and computational biology.

I have published relevant research in these areas at both machine learning venues (NeurIPSICLRICML-W) and biomedical venues and journals (BioinformaticsPLOS OneJCBPervasiveHealth). In particular, I am the first author of Graph Attention Networks—a popular convolutional layer for graphs—and Deep Graph Infomax—a scalable local/global unsupervised learning pipeline for graphs (featured in ZDNet).

Further, my research has been used in substantially improving the travel-time predictions in Google Maps (covered by outlets including the CNBCEndgadgetVentureBeatCNET, the Verge and ZDNet).

Contact Details

Room: 
GC01
Email: 

petarv@deepmind.com