activity
20182021
most citedCertifiable Robustness and Robust Training for Graph Convolutional Networks

106 citations · 136 across the 4 of their papers we have counts for

collaborators

7 papers

cs.LG20214 cited

A Study of Joint Graph Inference and Forecasting

Daniel Zügner, François-Xavier Aubet, Victor Garcia Satorras +3

We study a recent class of models which uses graph neural networks (GNNs) to improve forecasting in multivariate time series. The core assumption behind these models is that there…

cs.LG20212 cited

On Out-of-distribution Detection with Energy-based Models

Sven Elflein, Bertrand Charpentier, Daniel Zügner +1

Several density estimation methods have shown to fail to detect out-of-distribution (OOD) samples by assigning higher likelihoods to anomalous data. Energy-based models (EBMs) are…

cs.LG202024 cited

Reliable Graph Neural Networks via Robust Aggregation

Simon Geisler, Daniel Zügner, Stephan Günnemann

Perturbations targeting the graph structure have proven to be extremely effective in reducing the performance of Graph Neural Networks (GNNs), and traditional defenses such as adve…

cs.LG2020

Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts

Bertrand Charpentier, Daniel Zügner, Stephan Günnemann

Accurate estimation of aleatoric and epistemic uncertainty is crucial to build safe and reliable systems. Traditional approaches, such as dropout and ensemble methods, estimate unc…

cs.DS2019

Group Centrality Maximization for Large-scale Graphs

Eugenio Angriman, Alexander van der Grinten, Aleksandar Bojchevski +3

The study of vertex centrality measures is a key aspect of network analysis. Naturally, such centrality measures have been generalized to groups of vertices; for popular measures i…

cs.LG2019106 cited

Certifiable Robustness and Robust Training for Graph Convolutional Networks

Daniel Zügner, Stephan Günnemann

Recent works show that Graph Neural Networks (GNNs) are highly non-robust with respect to adversarial attacks on both the graph structure and the node attributes, making their outc…