28 citations · 66 across the 8 of their papers we have counts for
8 papers
DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees
Peter Müller, Lukas Faber, Karolis Martinkus +1
We propose the fully explainable Decision Tree Graph Neural Network (DT+GNN) architecture. In contrast to existing black-box GNNs and post-hoc explanation methods, the reasoning of…
Asynchronous Neural Networks for Learning in Graphs
Lukas Faber, Roger Wattenhofer
This paper studies asynchronous message passing (AMP), a new paradigm for applying neural network based learning to graphs. Existing graph neural networks use the synchronous distr…
DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
Pál András Papp, Karolis Martinkus, Lukas Faber +1
This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. In DropGNNs, we execute multiple runs…
Should Graph Neural Networks Use Features, Edges, Or Both?
Lukas Faber, Yifan Lu, Roger Wattenhofer
Graph Neural Networks (GNNs) are the first choice for learning algorithms on graph data. GNNs promise to integrate (i) node features as well as (ii) edge information in an end-to-e…
Towards Robust Graph Contrastive Learning
Nikola Jovanović, Zhao Meng, Lukas Faber +1
We study the problem of adversarially robust self-supervised learning on graphs. In the contrastive learning framework, we introduce a new method that increases the adversarial rob…
Contrastive Graph Neural Network Explanation
Lukas Faber, Amin K. Moghaddam, Roger Wattenhofer
Graph Neural Networks achieve remarkable results on problems with structured data but come as black-box predictors. Transferring existing explanation techniques, such as occlusion,…
Medley2K: A Dataset of Medley Transitions
Lukas Faber, Sandro Luck, Damian Pascual +3
The automatic generation of medleys, i.e., musical pieces formed by different songs concatenated via smooth transitions, is not well studied in the current literature. To facilitat…
Neural Status Registers
Lukas Faber, Roger Wattenhofer
Standard Neural Networks can learn mathematical operations, but they do not extrapolate. Extrapolation means that the model can apply to larger numbers, well beyond those observed…