5 citations · 11 across the 10 of their papers we have counts for
10 papers · 1 filter
A Unifying Relational Perspective on Expressive Lottery Tickets
Lorenz Kummer, Samir Moustafa, Anatol Ehrlich +4
Graph neural networks (GNNs) are widely used, but how parameter sparsity affects the expressivity of relational (RGNNs) and temporal (TGNNs) variants is poorly understood. The Stro…
XIMP: Cross Graph Inter-Message Passing for Molecular Property Prediction
Anatol Ehrlich, Lorenz Kummer, Vojtech Voracek +2
Accurate molecular property prediction is central to drug discovery, yet graph neural networks often underperform in data-scarce regimes and fail to surpass traditional fingerprint…
Visualization and Analysis of the Loss Landscape in Graph Neural Networks
Samir Moustafa, Lorenz Kummer, Simon Fetzel +2
Graph Neural Networks (GNNs) are powerful models for graph-structured data, with broad applications. However, the interplay between GNN parameter optimization, expressivity, and ge…
Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
Lorenz Kummer, Samir Moustafa, Anatol Ehrlich +4
The lottery ticket hypothesis (LTH) is well-studied for convolutional neural networks but has been validated only empirically for graph neural networks (GNNs), for which theoretica…
On the Relationship Between Robustness and Expressivity of Graph Neural Networks
Lorenz Kummer, Wilfried N. Gansterer, Nils M. Kriege
We investigate the vulnerability of Graph Neural Networks (GNNs) to bit-flip attacks (BFAs) by introducing an analytical framework to study the influence of architectural features,…
Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks
Lorenz Kummer, Samir Moustafa, Wilfried Gansterer +1
Bit Flip Attacks (BFAs) are a well-established class of adversarial attacks, originally developed for Convolutional Neural Networks within the computer vision domain. Most recently…
Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent
Lorenz Kummer, Samir Moustafa, Nils N. Kriege +1
Prior attacks on graph neural networks have mostly focused on graph poisoning and evasion, neglecting the network's weights and biases. Traditional weight-based fault injection att…
Neural Network Augmented Compartmental Pandemic Models
Lorenz Kummer, Kevin Sidak
Compartmental models are a tool commonly used in epidemiology for the mathematical modelling of the spread of infectious diseases, with their most popular representative being the…
Adaptive Precision Training (AdaPT): A dynamic fixed point quantized training approach for DNNs
Lorenz Kummer, Kevin Sidak, Tabea Reichmann +1
Quantization is a technique for reducing deep neural networks (DNNs) training and inference times, which is crucial for training in resource constrained environments or application…
Dynamic Neural Network Architectural and Topological Adaptation and Related Methods -- A Survey
Lorenz Kummer
Training and inference in deep neural networks (DNNs) has, due to a steady increase in architectural complexity and data set size, lead to the development of strategies for reducin…