1 code implementation • 9 Feb 2024 • Florian Grötschla, Joël Mathys, Robert Veres, Roger Wattenhofer
We introduce a scalable Graph Neural Network (GNN) based Graph Drawing framework with sub-quadratic runtime that can learn to optimize stress.
1 code implementation • 7 Jan 2024 • Philip Jordan, Florian Grötschla, Flint Xiaofeng Fan, Roger Wattenhofer
We provide the first decentralized Byzantine fault-tolerant FRL method.
1 code implementation • 30 Oct 2023 • Stefan Künzli, Florian Grötschla, Joël Mathys, Roger Wattenhofer
We propose SURF, a benchmark designed to test the $\textit{generalization}$ of learned graph-based fluid simulators.
no code implementations • 10 Oct 2023 • Joël Mathys, Florian Grötschla, Kalyan Varma Nadimpalli, Roger Wattenhofer
However, this raises two core questions i) How can we enable nodes to gather the required information in a given graph ($\textit{information exchange}$), even if is far away and ii) How can we design an execution framework which enables this information exchange for extrapolation to larger graph sizes ($\textit{algorithmic alignment for extrapolation}$).
1 code implementation • 21 Sep 2023 • Julian Minder, Florian Grötschla, Joël Mathys, Roger Wattenhofer
We introduce an extension to the CLRS algorithmic learning benchmark, prioritizing scalability and the utilization of sparse representations.
1 code implementation • 30 Jun 2023 • Eren Akbiyik, Florian Grötschla, Beni Egressy, Roger Wattenhofer
We use Graphtester to analyze over 40 different graph datasets, determining upper bounds on the performance of various GNNs based on the number of layers.
1 code implementation • 14 Mar 2023 • Moritz Neun, Christian Eichenberger, Henry Martin, Markus Spanring, Rahul Siripurapu, Daniel Springer, Leyan Deng, Chenwang Wu, Defu Lian, Min Zhou, Martin Lumiste, Andrei Ilie, Xinhua Wu, Cheng Lyu, Qing-Long Lu, Vishal Mahajan, Yichao Lu, Jiezhang Li, Junjun Li, Yue-Jiao Gong, Florian Grötschla, Joël Mathys, Ye Wei, He Haitao, Hui Fang, Kevin Malm, Fei Tang, Michael Kopp, David Kreil, Sepp Hochreiter
We only provide vehicle count data from spatially sparse stationary vehicle detectors in these three cities as model input for this task.
1 code implementation • 9 Dec 2022 • Florian Grötschla, Joël Mathys, Roger Wattenhofer
In order to scale, we focus on a recurrent architecture design that can learn simple graph problems end to end on smaller graphs and then extrapolate to larger instances.
2 code implementations • 21 Nov 2022 • Florian Grötschla, Joël Mathys
Traffic4cast is an annual competition to predict spatio temporal traffic based on real world data.