Search Results for author: Florian Grötschla

Found 11 papers, 9 papers with code

Benchmarking GNNs Using Lightning Network Data

no code implementations5 Jul 2024 Rainer Feichtinger, Florian Grötschla, Lioba Heimbach, Roger Wattenhofer

Nodes announce their channels to the network, forming a graph with channels as edges.

Benchmarking

Next Level Message-Passing with Hierarchical Support Graphs

1 code implementation22 Jun 2024 Carlos Vonessen, Florian Grötschla, Roger Wattenhofer

Message-Passing Neural Networks (MPNNs) are extensively employed in graph learning tasks but suffer from limitations such as the restricted scope of information exchange, by being confined to neighboring nodes during each round of message passing.

Graph Learning

CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs

1 code implementation9 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.

Graph Neural Network

SURF: A Generalization Benchmark for GNNs Predicting Fluid Dynamics

1 code implementation30 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.

Flood and Echo Net: Algorithmically Aligned GNNs that Generalize

no code implementations10 Oct 2023 Joël Mathys, Florian Grötschla, Kalyan Varma Nadimpalli, Roger Wattenhofer

We test the Flood and Echo Net on a variety of synthetic tasks and the SALSA-CLRS benchmark and find that the algorithmic alignment of the execution improves generalization to larger graph sizes.

Distributed Computing

SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning

1 code implementation21 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.

Graphtester: Exploring Theoretical Boundaries of GNNs on Graph Datasets

1 code implementation30 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.

Learning Graph Algorithms With Recurrent Graph Neural Networks

1 code implementation9 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.

Hierarchical Graph Structures for Congestion and ETA Prediction

2 code implementations21 Nov 2022 Florian Grötschla, Joël Mathys

Traffic4cast is an annual competition to predict spatio temporal traffic based on real world data.

Cannot find the paper you are looking for? You can Submit a new open access paper.