2026 Stephan Günnemann: Computer Science Researcher – H-Index, Publications & Awards

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Computer Science	49	5867	5700	272	264	218	10004

Overview

Stephan Günnemann is affiliated with the Technical University of Munich in Germany, where they have contributed extensively to the field of Computer Science. Their research output includes 286 publications, with a strong focus on Artificial Intelligence represented by 187 papers. Additional subfields of study include Materials Chemistry, Computer Vision and Pattern Recognition, Computational Theory and Mathematics, and Computer Networks and Communications.

The scientist's work covers several specific research topics:

Adversarial Robustness in Machine Learning
Advanced Graph Neural Networks
Machine Learning in Materials Science
Anomaly Detection Techniques and Applications
Computational Drug Discovery Methods
Neural Networks and Applications
Explainable Artificial Intelligence (XAI)

Stephan Günnemann has a notable presence in a variety of publication venues, with a significant number of papers featured in arXiv (Cornell University), totaling 150 contributions. Other frequent venues include Data Mining and Knowledge Discovery, Journal of Hydrology, CentAUR (University of Reading), and Machine Learning.

Frequent co-authors include Bertrand Charpentier, Daniel Zügner, Tom Wollschläger, Leo Schwinn, and Simon Geisler. These collaborations indicate an active engagement within their research community.

Some of the recent papers linked to their work include:

ChatGPT for good? On opportunities and challenges of large language models for education, 2023, Learning and Individual Differences
Directional Message Passing for Molecular Graphs, 2020, arXiv (Cornell University)
Predicting cellular responses to complex perturbations in high-throughput screens, 2023, Molecular Systems Biology
Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules, 2020, arXiv (Cornell University)
GemNet: Universal Directional Graph Neural Networks for Molecules, 2021, arXiv (Cornell University)

Best Publications

Adversarial Attacks on Neural Networks for Graph Data.

Daniel Zügner;Amir Akbarnejad;Stephan Günnemann

1112
Citations
Pitfalls of Graph Neural Network Evaluation.

Oleksandr Shchur;Maximilian Mumme;Aleksandar Bojchevski;Stephan Günnemann

774
Citations
Predict then Propagate: Graph Neural Networks meet Personalized PageRank

Johannes Klicpera;Aleksandar Bojchevski;Stephan Günnemann

484
Citations
Evaluating Clustering in Subspace Projections of High Dimensional Data

Emmanuel Müller;Stephan Günnemann;Ira Assent;Thomas Seidl

427
Citations
Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking

Aleksandar Bojchevski;Stephan Günnemann

410
Citations
Adversarial Attacks on Graph Neural Networks via Meta Learning

Daniel Zügner;Stephan Günnemann

397
Citations
Scaling Graph Neural Networks with Approximate PageRank

Aleksandar Bojchevski;Johannes Klicpera;Bryan Perozzi;Amol Kapoor

344
Citations
NetGAN: Generating Graphs via Random Walks

Aleksandar Bojchevski;Oleksandr Shchur;Daniel Zügner;Stephan Günnemann

254
Citations
Directional Message Passing for Molecular Graphs

Johannes Klicpera;Janek Groß;Stephan Günnemann

231
Citations
Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift

Stephan Rabanser;Stephan Günnemann;Zachary C. Lipton

196
Citations
Certifiable Robustness and Robust Training for Graph Convolutional Networks

Daniel Zügner;Stephan Günnemann

187
Citations
Adversarial Attacks on Node Embeddings via Graph Poisoning

Aleksandar Bojchevski;Stephan Günnemann

184
Citations
Introduction to Tensor Decompositions and their Applications in Machine Learning.

Stephan Rabanser;Oleksandr Shchur;Stephan Günnemann

183
Citations
Mining coherent subgraphs in multi-layer graphs with edge labels

Brigitte Boden;Stephan Günnemann;Holger Hoffmann;Thomas Seidl

162
Citations
On Using Class-Labels in Evaluation of Clusterings

Ines Färber;Stephan Günnemann;Hans-Peter Kriegel;Peer Kröger

152
Citations
Subspace Clustering Meets Dense Subgraph Mining: A Synthesis of Two Paradigms

Stephan Gunnemann;Ines Farber;Brigitte Boden;Thomas Seidl

149
Citations
Diffusion Improves Graph Learning

Johannes Klicpera;Stefan Weißenberger;Stephan Günnemann

132
Citations
Com2: Fast Automatic Discovery of Temporal ( Comet ) Communities

Miguel Araujo;Miguel Araujo;Spiros Papadimitriou;Stephan Günnemann;Christos Faloutsos

126
Citations
BIRDNEST: Bayesian Inference for Ratings-Fraud Detection.

Bryan Hooi;Neil Shah;Alex Beutel;Stephan Günnemann

121
Citations
Relevant Subspace Clustering: Mining the Most Interesting Non-redundant Concepts in High Dimensional Data

Emmanuel Müller;Ira Assent;Stephan Günnemann;Ralph Krieger

96
Citations
Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules.

Johannes Klicpera;Shankari Giri;Johannes T. Margraf;Stephan Günnemann

36
Citations
Predict then Propagate: Combining neural networks with personalized pagerank for classification on graphs

Johannes Klicpera;Aleksandar Bojchevski;Stephan Günnemann

6
Citations

Frequent Co-Authors

Thomas Seidl Ludwig-Maximilians-Universität München

Christos Faloutsos Carnegie Mellon University

Ira Assent Aarhus University

Alfons Kemper Technical University of Munich

Thomas Neumann Technical University of Munich

Volker Tresp Ludwig-Maximilians-Universität München

Danai Koutra University of Michigan–Ann Arbor

Alex Beutel OpenAI

Leman Akoglu Carnegie Mellon University

Patrick van der Smagt Volkswagen Group (United States)

External Links

Personal website of Stephan Günnemann Google Scholar page

If you think any of the details on this page are incorrect, let us know.

Related Online Degrees & Career Pathways

Exploring computer science opens up diverse online study options and career opportunities. Many students seek cheap online universities to complete their bachelor’s degree with lower tuition costs and added flexibility. Accredited programs in the USA allow you to balance coursework with work or family commitments, often with the same curriculum as on-campus options.

Looking to expand your technical expertise? It’s now possible to get an engineering degree online in specialized fields like software, computer, or systems engineering. Pursuing related fields such as management or education can also be done virtually.

For professionals aiming for leadership, an cheapest executive mba online is a practical pathway to gain advanced business skills alongside your tech background. Furthermore, if you’re interested in information management, earning an online library science degree is a great option, opening doors to digital information roles in both academic and corporate settings.

Exploring these related online degrees can help tailor your education to meet your professional goals and broaden your career prospects in the digital age.