I am happy to announce that our group has six papers accepted at NeurIPS 2021! With works on ML for graphs, TPPs and flows, as well as robustness of ML methods and uncertainty, all of our core research directions are represented. Congratulations to my PhD students for this great success.
- Simon Geisler, Tobias Schmidt, Hakan Şirin, Daniel Zügner, Aleksandar Bojchevski, Stephan Günnemann
Robustness of Graph Neural Networks at Scale - Johannes Klicpera, Florian Becker, Stephan Günnemann
GemNet: Universal Directional Graph Neural Networks for Molecules
[Preprint] - Maximilian Stadler, Bertrand Charpentier, Simon Geisler, Daniel Zügner, Stephan Günnemann
Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification - Marin Biloš, Johanna Sommer, Syama Sundar Rangapuram, Tim Januschowski, Stephan Günnemann
Neural Flows: Efficient Alternative to Neural ODEs
[Preprint] - Johannes Klicpera, Chandan Yeshwanth, Stephan Günnemann
Directional Message Passing on Molecular Graphs via Synthetic Coordinates - Oleksandr Shchur, Ali Caner Turkmen, Tim Januschowski, Jan Gasthaus, Stephan Günnemann
Detecting Anomalous Event Sequences with Temporal Point Processes
[Preprint]
Additionally, we have one paper at the Datasets and Benchmarks Track:
- Johannes C. Paetzold, Julian McGinnis, Suprosanna Shit, Ivan Ezhov, Paul Büschl, Chinmay Prabhakar, Anjany Sekuboyina, Mihail Todorov, Georgios Kaissis, Ali Ertürk, Stephan Günnemann, Björn Menze
Whole Brain Vessel Graphs: A Dataset and Benchmark for Graph Learning and Neuroscience