5 papers · 1 filter
Is BatchEnsemble a Single Model? On Calibration and Diversity of Efficient Ensembles
Anton Zamyatin, Patrick Indri, Sagar Malhotra +1
In resource-constrained and low-latency settings, uncertainty estimates must be efficiently obtained. Deep Ensembles provide robust epistemic uncertainty (EU) but require training…
Probably Approximately Global Robustness Certification
Peter Blohm, Patrick Indri, Thomas Gärtner +1
We propose and investigate probabilistic guarantees for the adversarial robustness of classification algorithms. While traditional formal verification approaches for robustness are…
WILTing Trees: Interpreting the Distance Between MPNN Embeddings
Masahiro Negishi, Thomas Gärtner, Pascal Welke
We investigate the distance function learned by message passing neural networks (MPNNs) in specific tasks, aiming to capture the functional distance between prediction targets that…
Towards Foundation Models on Graphs: An Analysis on Cross-Dataset Transfer of Pretrained GNNs
Fabrizio Frasca, Fabian Jogl, Moshe Eliasof +4
To develop a preliminary understanding towards Graph Foundation Models, we study the extent to which pretrained Graph Neural Networks can be applied across datasets, an effort requ…
Logical Distillation of Graph Neural Networks
Alexander Pluska, Pascal Welke, Thomas Gärtner +1
We present a logic based interpretable model for learning on graphs and an algorithm to distill this model from a Graph Neural Network (GNN). Recent results have shown connections…