P
Petar Veličković
Researcher at Google
Publications - 81
Citations - 11982
Petar Veličković is an academic researcher from Google. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 17, co-authored 67 publications receiving 5951 citations. Previous affiliations of Petar Veličković include University of Cambridge.
Papers
More filters
Proceedings ArticleDOI
Graph Attention Networks
TL;DR: Graph Attention Networks (GATs) as mentioned in this paper leverage masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.
Posted Content
Graph Attention Networks
TL;DR: Graph Attention Networks (GATs) as discussed by the authors leverage masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.
Posted Content
Deep Graph Infomax.
TL;DR: Deep Graph Infomax (DGI) is presented, a general approach for learning node representations within graph-structured data in an unsupervised manner that is readily applicable to both transductive and inductive learning setups.
Proceedings ArticleDOI
Deep Graph Infomax
TL;DR: Deep Graph Infomax (DGI) as discussed by the authors is a general approach for learning node representations within graph-structured data in an unsupervised manner, which relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs.
Proceedings Article
Principal Neighbourhood Aggregation for Graph Nets
TL;DR: This work proposes Principal Neighbourhood Aggregation (PNA), a novel architecture combining multiple aggregators with degree-scalers (which generalize the sum aggregator) and compares the capacity of different models to capture and exploit the graph structure via a novel benchmark containing multiple tasks taken from classical graph theory.