Hello, and welcome to one of my homes on the web! I’m Petar, a Research Scientist at DeepMind. I have a PhD in Computer Science from the University of Cambridge (Trinity College), obtained under the supervision of Pietro Liò. My research interests involve devising neural network architectures that operate on nontrivially structured data (such as graphs), and their applications in algorithmic reasoning and computational biology. 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. My research has been featured in media outlets such as ZDNet.
New paper on pointer-base mechanisms for GNNs:Pointer Graph Networks out now on the arXiv
Gave an invited talk on Graph Representation Learning for Algorithmic Reasoning at the Deep Learning for Graphs Workshop at WWW'20
New paper on GNN expressive power: Principal Neighbourhood Aggregation for Graph Nets out now on the arXiv