Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Roger Wattenhofer

Roger Wattenhofer

Agent-based Graph Neural Networks

Karolis Martinkus , Pál András Papp , Benedikt Schesch , Roger Wattenhofer

Figure 1 for Agent-based Graph Neural Networks

Figure 2 for Agent-based Graph Neural Networks

Figure 3 for Agent-based Graph Neural Networks

Figure 4 for Agent-based Graph Neural Networks

* 26 pages, 3 figures

Access Paper or Ask Questions

A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications

Lukas Wolf , Ard Kastrati , Martyna Beata Płomecka , Jie-Ming Li , Dustin Klebe , Alexander Veicht , Roger Wattenhofer , Nicolas Langer

Figure 1 for A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications

Figure 2 for A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications

Figure 3 for A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications

Figure 4 for A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications

* 21 pages, Published at the Proceedings of the 39th International Conference on Machine Learning (ICML) 2022

Access Paper or Ask Questions

Graph Neural Networks with Precomputed Node Features

Beni Egressy , Roger Wattenhofer

Figure 1 for Graph Neural Networks with Precomputed Node Features

Figure 2 for Graph Neural Networks with Precomputed Node Features

Figure 3 for Graph Neural Networks with Precomputed Node Features

Figure 4 for Graph Neural Networks with Precomputed Node Features

Access Paper or Ask Questions

DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees

Peter Müller , Lukas Faber , Karolis Martinkus , Roger Wattenhofer

Figure 1 for DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees

Figure 2 for DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees

Figure 3 for DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees

Figure 4 for DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees

Access Paper or Ask Questions

Asynchronous Neural Networks for Learning in Graphs

Lukas Faber , Roger Wattenhofer

Figure 1 for Asynchronous Neural Networks for Learning in Graphs

Figure 2 for Asynchronous Neural Networks for Learning in Graphs

Figure 3 for Asynchronous Neural Networks for Learning in Graphs

Figure 4 for Asynchronous Neural Networks for Learning in Graphs

Access Paper or Ask Questions

SPECTRE : Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

Karolis Martinkus , Andreas Loukas , Nathanaël Perraudin , Roger Wattenhofer

Figure 1 for SPECTRE : Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

Figure 2 for SPECTRE : Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

Figure 3 for SPECTRE : Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

Figure 4 for SPECTRE : Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

* 20 pages, 10 figures

Access Paper or Ask Questions

A Theoretical Comparison of Graph Neural Network Extensions

Pál András Papp , Roger Wattenhofer

Figure 1 for A Theoretical Comparison of Graph Neural Network Extensions

Figure 2 for A Theoretical Comparison of Graph Neural Network Extensions

Figure 3 for A Theoretical Comparison of Graph Neural Network Extensions

Figure 4 for A Theoretical Comparison of Graph Neural Network Extensions

Access Paper or Ask Questions

The Price of Majority Support

Robin Fritsch , Roger Wattenhofer

Figure 1 for The Price of Majority Support

Figure 2 for The Price of Majority Support

Figure 3 for The Price of Majority Support

Figure 4 for The Price of Majority Support

* 9 pages, 2 figures

Access Paper or Ask Questions

DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

Pál András Papp , Karolis Martinkus , Lukas Faber , Roger Wattenhofer

Figure 1 for DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

Figure 2 for DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

Figure 3 for DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

Figure 4 for DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

* Published in the 35th Conference on Neural Information Processing Systems (NeurIPS 2021)

Access Paper or Ask Questions

EEGEyeNet: a Simultaneous Electroencephalography and Eye-tracking Dataset and Benchmark for Eye Movement Prediction

Ard Kastrati , Martyna Beata Płomecka , Damián Pascual , Lukas Wolf , Victor Gillioz , Roger Wattenhofer , Nicolas Langer

Figure 1 for EEGEyeNet: a Simultaneous Electroencephalography and Eye-tracking Dataset and Benchmark for Eye Movement Prediction

Figure 2 for EEGEyeNet: a Simultaneous Electroencephalography and Eye-tracking Dataset and Benchmark for Eye Movement Prediction

Figure 3 for EEGEyeNet: a Simultaneous Electroencephalography and Eye-tracking Dataset and Benchmark for Eye Movement Prediction

Figure 4 for EEGEyeNet: a Simultaneous Electroencephalography and Eye-tracking Dataset and Benchmark for Eye Movement Prediction

* Published at NeurIPS 2021 Datasets and Benchmarks Track

Access Paper or Ask Questions