Our group has four papers accepted at NeurIPS 2020, including one oral presentation (top 1% of submitted works)!
The works cover the full range of our core research topics: machine learning for graphs, machine learning for temporal data, and reliability of ML methods, i.e. robustness & uncertainty.
-
Fast and Flexible Temporal Point Processes with Triangular Maps (oral)
Oleksandr Shchur, Nicholas Gao, Marin Biloš, Stephan Günnemann
preprint -
Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
Bertrand Charpentier, Daniel Zügner, Stephan Günnemann
preprint -
Reliable Graph Neural Networks via Robust Location Estimation
Simon Geisler, Daniel Zügner, Stephan Günnemann -
Deep Rao-Blackwellised Particle Filters for Time Series Forecasting
Richard Kurle, Syama Sundar Rangapuram, Emmanuel de Bézenac, Stephan Günnemann, Jan Gasthaus
joint work with Amazon Research
Congratulations to all co-authors!