J
Johannes Klicpera
Researcher at Technische Universität München
Publications - 22
Citations - 2417
Johannes Klicpera is an academic researcher from Technische Universität München. The author has contributed to research in topics: Message passing & PageRank. The author has an hindex of 11, co-authored 22 publications receiving 1002 citations.
Papers
More filters
Proceedings Article
Predict then Propagate: Graph Neural Networks meet Personalized PageRank
TL;DR: This paper uses the relationship between graph convolutional networks (GCN) and PageRank to derive an improved propagation scheme based on personalized PageRank, and constructs a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP.
Proceedings Article
Directional Message Passing for Molecular Graphs
TL;DR: This work proposes a message passing scheme analogous to belief propagation, which uses the directional information by transforming messages based on the angle between them, and uses spherical Bessel functions to construct a theoretically well-founded, orthogonal radial basis that achieves better performance than the currently prevalent Gaussian radial basis functions while using more than 4x fewer parameters.
Posted Content
Predict then Propagate: Graph Neural Networks meet Personalized PageRank
TL;DR: In this article, the relationship between graph convolutional networks (GCN) and PageRank was used to derive an improved propagation scheme based on personalized PageRank, which leverages a large, adjustable neighborhood for classification and can be easily combined with any neural network.
Posted Content
Diffusion Improves Graph Learning
TL;DR: This work removes the restriction of using only the direct neighbors by introducing a powerful, yet spatially localized graph convolution: Graph diffusion convolution (GDC), which leverages generalized graph diffusion and alleviates the problem of noisy and often arbitrarily defined edges in real graphs.
Proceedings ArticleDOI
Scaling Graph Neural Networks with Approximate PageRank
Aleksandar Bojchevski,Johannes Klicpera,Bryan Perozzi,Amol Kapoor,Martin Blais,Benedek Rozemberczki,Michal Lukasik,Stephan Günnemann +7 more
TL;DR: The PPRGo model is presented, which utilizes an efficient approximation of information diffusion in GNNs resulting in significant speed gains while maintaining state-of-the-art prediction performance, and the practical application of PPR go to solve large-scale node classification problems at Google.