activity
20182021
most citedHierarchical Inter-Message Passing for Learning on Molecular Graphs

36 citations · 47 across the 3 of their papers we have counts for

collaborators

5 papers

cs.LG202111 cited

GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings

Matthias Fey, Jan E. Lenssen, Frank Weichert +1

We present GNNAutoScale (GAS), a framework for scaling arbitrary message-passing GNNs to large graphs. GAS prunes entire sub-trees of the computation graph by utilizing historical…

physics.soc-ph2020

Agent-based Simulation of Pedestrian Dynamics for Exposure Time Estimation in Epidemic Risk Assessment

Thomas Harweg, Daniel Bachmann, Frank Weichert

With the Corona Virus Disease 2019 (COVID-19) pandemic spreading across the world, protective measures for containing the virus are essential, especially as long as no vaccine or e…

cs.LG202036 cited

Hierarchical Inter-Message Passing for Learning on Molecular Graphs

Matthias Fey, Jan-Gin Yuen, Frank Weichert

We present a hierarchical neural message passing architecture for learning on molecular graphs. Our model takes in two complementary graph representations: the raw molecular graph…

cs.CV2020

Adversarial Generation of Continuous Implicit Shape Representations

Marian Kleineberg, Matthias Fey, Frank Weichert

This work presents a generative adversarial architecture for generating three-dimensional shapes based on signed distance representations. While the deep generation of shapes has b…

cs.CV2018

Recognizing Cuneiform Signs Using Graph Based Methods

Nils M. Kriege, Matthias Fey, Denis Fisseler +2

The cuneiform script constitutes one of the earliest systems of writing and is realized by wedge-shaped marks on clay tablets. A tremendous number of cuneiform tablets have already…