Research Group Stephan Günnemann
Stephan Günnemann
Prof. Dr.
Principal Investigator
Stephan Günnemann
is Professor of Data Analytics and Machine Learning at TU Munich.
He conducts research in the area of machine learning and data analytics. His main research focuses on how to make machine learning techniques reliable, thus, enabling their safe and robust use in various application domains. He is particularly interested in studying machine learning methods targeting complex data domains such as graphs/networks and temporal data.
Team members @MCML
PhD Students
Lukas Gosch
→ Group Stephan Günnemann
Data Analytics & Machine Learning
Filippo Guerranti
→ Group Stephan Günnemann
Data Analytics & Machine Learning
Marcel Kollovieh
→ Group Stephan Günnemann
Data Analytics & Machine Learning
Aman Saxena
→ Group Stephan Günnemann
Data Analytics & Machine Learning
Recent News @MCML
Publications @MCML
2025
[39]
S. Schmidt • J. Koerner • D. Fuchsgruber • S. Gasperini • F. Tombari • S. Günnemann
Prior2Former - Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation.
ICCV 2025 - IEEE/CVF International Conference on Computer Vision. Honolulu, Hawai’i, Oct 19-23, 2025. To be published. Preprint available. URL
Prior2Former - Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation.
ICCV 2025 - IEEE/CVF International Conference on Computer Vision. Honolulu, Hawai’i, Oct 19-23, 2025. To be published. Preprint available. URL
[38]
P. Foth • L. Gosch • S. Geisler • L. Schwinn • S. Günnemann
Adversarial Robustness of Graph Transformers.
Transactions on Machine Learning Research. Oct. 2025. URL
Adversarial Robustness of Graph Transformers.
Transactions on Machine Learning Research. Oct. 2025. URL
[37]
M. Lienen • A. Saydemir • S. Günnemann
UnHiPPO: Uncertainty-aware Initialization for State Space Models.
ICML 2025 - 42nd International Conference on Machine Learning. Vancouver, Canada, Jul 13-19, 2025. URL
UnHiPPO: Uncertainty-aware Initialization for State Space Models.
ICML 2025 - 42nd International Conference on Machine Learning. Vancouver, Canada, Jul 13-19, 2025. URL
[36]
L. Gosch • M. Sabanayagam • D. Ghoshdastidar • S. Günnemann
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks.
Transactions on Machine Learning Research. Jun. 2025. URL
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks.
Transactions on Machine Learning Research. Jun. 2025. URL
[35]
M. Kollovieh • M. Lienen • D. Lüdke • L. Schwinn • S. Günnemann
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL
[34]
M. Sabanayagam • L. Gosch • S. Günnemann • D. Ghoshdastidar
Exact Certification of (Graph) Neural Networks Against Label Poisoning.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Spotlight Presentation. URL GitHub
Exact Certification of (Graph) Neural Networks Against Label Poisoning.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Spotlight Presentation. URL GitHub
[33]
M. Scherbela • N. Gao • P. Grohs • S. Günnemann
Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems.
Preprint (Apr. 2025). arXiv
Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems.
Preprint (Apr. 2025). arXiv
2024
[32]
L. Gosch • M. Sabanayagam • D. Ghoshdastidar • S. Günnemann
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks.
AdvML-Frontiers @NeurIPS 2024 - 3rd Workshop on New Frontiers in Adversarial Machine Learning at the 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. URL
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks.
AdvML-Frontiers @NeurIPS 2024 - 3rd Workshop on New Frontiers in Adversarial Machine Learning at the 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. URL
[31]
R. Dhahri • A. Immer • B. Charpentier • S. Günnemann • V. Fortuin
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. URL
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. URL
[30]
M. Kollovieh • B. Charpentier • D. Zügner • S. Günnemann
Expected Probabilistic Hierarchies.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. URL
Expected Probabilistic Hierarchies.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. URL
[29]
M. Kollovieh • L. Gosch • M. Lienen • Y. Scholten • L. Schwinn • S. Günnemann
Assessing Robustness via Score-Based Adversarial Image Generation.
Transactions on Machine Learning Research. Dec. 2024. URL
Assessing Robustness via Score-Based Adversarial Image Generation.
Transactions on Machine Learning Research. Dec. 2024. URL
[28]
J. G. Wiese • L. Wimmer • T. Papamarkou • B. Bischl • S. Günnemann • D. Rügamer
Towards Efficient Posterior Sampling in Deep Neural Networks via Symmetry Removal (Extended Abstract).
IJCAI 2024 - 33rd International Joint Conference on Artificial Intelligence. Jeju, Korea, Aug 03-09, 2024. DOI
Towards Efficient Posterior Sampling in Deep Neural Networks via Symmetry Removal (Extended Abstract).
IJCAI 2024 - 33rd International Joint Conference on Artificial Intelligence. Jeju, Korea, Aug 03-09, 2024. DOI
[27]
P. Foth • L. Gosch • S. Geisler • L. Schwinn • S. Günnemann
Relaxing Graph Transformers for Adversarial Attacks.
Differentiable Almost Everything @ICML 2024 - Workshop Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators at the 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. PDF
Relaxing Graph Transformers for Adversarial Attacks.
Differentiable Almost Everything @ICML 2024 - Workshop Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators at the 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. PDF
[26]
T. Wollschläger • N. Kemper • L. Hetzel • J. Sommer • S. Günnemann
Expressivity and Generalization: Fragment-Biases for Molecular GNNs.
Preprint (Jun. 2024). arXiv
Expressivity and Generalization: Fragment-Biases for Molecular GNNs.
Preprint (Jun. 2024). arXiv
2023
[25]
Y. Scholten • J. Schuchardt • A. Bojchevski • S. Günnemann
Hierarchical randomized smoothing.
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Dec 10-16, 2023. URL
Hierarchical randomized smoothing.
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Dec 10-16, 2023. URL
[24]
J. Schuchardt • Y. Scholten • S. Günnemann
Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More.
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Dec 10-16, 2023. URL
Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More.
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Dec 10-16, 2023. URL
[23]
J. G. Wiese • L. Wimmer • T. Papamarkou • B. Bischl • S. Günnemann • D. Rügamer
Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry.
ECML-PKDD 2023 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Turin, Italy, Sep 18-22, 2023. Best Paper Award. DOI
Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry.
ECML-PKDD 2023 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Turin, Italy, Sep 18-22, 2023. Best Paper Award. DOI
[22]
M. Biloš • K. Rasul • A. Schneider • Y. Nevmyvaka • S. Günnemann
Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion.
ICML 2023 - 40th International Conference on Machine Learning. Honolulu, Hawaii, Jul 23-29, 2023. URL
Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion.
ICML 2023 - 40th International Conference on Machine Learning. Honolulu, Hawaii, Jul 23-29, 2023. URL
[21]
T. Wollschläger • N. Gao • B. Charpentier • M. A. Ketata • S. Günnemann
Uncertainty Estimation for Molecules: Desiderata and Methods.
ICML 2023 - 40th International Conference on Machine Learning. Honolulu, Hawaii, Jul 23-29, 2023. URL
Uncertainty Estimation for Molecules: Desiderata and Methods.
ICML 2023 - 40th International Conference on Machine Learning. Honolulu, Hawaii, Jul 23-29, 2023. URL
[20]
M. Lotfollahi • A. K. Susmelj • C. De Donno • L. Hetzel • Y. Ji • I. L. Ibarra • S. R. Srivatsan • M. Naghipourfar • R. M. Daza • B. Martin • J. Shendure • J. L. McFaline‐Figueroa • P. Boyeau • F. A. Wolf • N. Yakubova • S. Günnemann • C. Trapnell • D. Lopez‐Paz • F. J. Theis
Predicting cellular responses to complex perturbations in high‐throughput screens.
Molecular Systems Biology 19.e11517. Jun. 2023. DOI
Predicting cellular responses to complex perturbations in high‐throughput screens.
Molecular Systems Biology 19.e11517. Jun. 2023. DOI
[19]
J. Sommer • L. Hetzel • D. Lüdke • F. J. Theis • S. Günnemann
The power of motifs as inductive bias for learning molecular distributions.
Preprint (Jun. 2023). arXiv
The power of motifs as inductive bias for learning molecular distributions.
Preprint (Jun. 2023). arXiv
[18]
R. Paolino • A. Bojchevski • S. Günnemann • G. Kutyniok • R. Levie
Unveiling the Sampling Density in Non-Uniform Geometric Graphs.
ICLR 2023 - 11th International Conference on Learning Representations. Kigali, Rwanda, May 01-05, 2023. URL
Unveiling the Sampling Density in Non-Uniform Geometric Graphs.
ICLR 2023 - 11th International Conference on Learning Representations. Kigali, Rwanda, May 01-05, 2023. URL
2022
[17]
O. Shchur
Modeling Continuous-time Event Data with Neural Temporal Point Processes.
Dissertation TU München. Dec. 2022. URL
Modeling Continuous-time Event Data with Neural Temporal Point Processes.
Dissertation TU München. Dec. 2022. URL
[16]
L. Hetzel • S. Boehm • N. Kilbertus • S. Günnemann • M. Lotfollahi • F. J. Theis
Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution.
NeurIPS 2022 - 36th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Nov 28-Dec 09, 2022. URL
Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution.
NeurIPS 2022 - 36th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Nov 28-Dec 09, 2022. URL
[15]
Y. Scholten • J. Schuchardt • S. Geisler • A. Bojchevski • S. Günnemann
Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks.
NeurIPS 2022 - 36th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Nov 28-Dec 09, 2022. URL
Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks.
NeurIPS 2022 - 36th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Nov 28-Dec 09, 2022. URL
[14]
L. Hetzel • S. Boehm • N. Kilbertus • S. Günnemann • M. Lotfollahi • F. J. Theis
Predicting single-cell perturbation responses for unseen drugs.
MLDD @ICML 2022 - Workshop on Machine Learning for Drug Discovery at the 39th International Conference on Machine Learning. Baltimore, MD, USA, Jul 17-23, 2022. URL
Predicting single-cell perturbation responses for unseen drugs.
MLDD @ICML 2022 - Workshop on Machine Learning for Drug Discovery at the 39th International Conference on Machine Learning. Baltimore, MD, USA, Jul 17-23, 2022. URL
[13]
2021
[12]
L. Hetzel • D. S. Fischer • S. Günnemann • F. J. Theis
Graph representation learning for single-cell biology.
Current Opinion in Systems Biology 28.100347. Dec. 2021. DOI
Graph representation learning for single-cell biology.
Current Opinion in Systems Biology 28.100347. Dec. 2021. DOI
[11]
M. Biloš • S. Günnemann
Scalable Normalizing Flows for Permutation Invariant Densities.
ICML 2021 - 38th International Conference on Machine Learning. Virtual, Jul 18-24, 2021. URL
Scalable Normalizing Flows for Permutation Invariant Densities.
ICML 2021 - 38th International Conference on Machine Learning. Virtual, Jul 18-24, 2021. URL
[10]
J. Schuchardt • A. Bojchevski • J. Gasteiger • S. Günnemann
Collective Robustness Certificates - Exploiting Interdependence in Graph Neural Networks.
ICLR 2021 - 9th International Conference on Learning Representations. Virtual, May 03-07, 2021. URL
Collective Robustness Certificates - Exploiting Interdependence in Graph Neural Networks.
ICLR 2021 - 9th International Conference on Learning Representations. Virtual, May 03-07, 2021. URL
2020
[9]
S. Geisler • D. Zügner • S. Günnemann
Reliable Graph Neural Networks via Robust Aggregation.
NeurIPS 2020 - 34th Conference on Neural Information Processing Systems. Virtual, Dec 06-12, 2020. URL
Reliable Graph Neural Networks via Robust Aggregation.
NeurIPS 2020 - 34th Conference on Neural Information Processing Systems. Virtual, Dec 06-12, 2020. URL
[8]
O. Shchur • N. Gao • M. Biloš • S. Günnemann
Fast and Flexible Temporal Point Processes with Triangular Maps.
NeurIPS 2020 - 34th Conference on Neural Information Processing Systems. Virtual, Dec 06-12, 2020. URL
Fast and Flexible Temporal Point Processes with Triangular Maps.
NeurIPS 2020 - 34th Conference on Neural Information Processing Systems. Virtual, Dec 06-12, 2020. URL
[7]
D. Zügner • S. Günnemann
Certifiable Robustness of Graph Convolutional Networks under Structure Perturbation.
KDD 2020 - 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Diego, California, USA, Aug 23-27, 2020. DOI
Certifiable Robustness of Graph Convolutional Networks under Structure Perturbation.
KDD 2020 - 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Diego, California, USA, Aug 23-27, 2020. DOI
[6]
J. Klicpera • J. Groß • S. Günnemann
Directional Message Passing for Molecular Graphs.
ICLR 2020 - 8th International Conference on Learning Representations. Virtual, Apr 26-May 01, 2020. URL
Directional Message Passing for Molecular Graphs.
ICLR 2020 - 8th International Conference on Learning Representations. Virtual, Apr 26-May 01, 2020. URL
[5]
O. Shchur • M. Biloš • S. Günnemann
Intensity-Free Learning of Temporal Point Processes.
ICLR 2020 - 8th International Conference on Learning Representations. Virtual, Apr 26-May 01, 2020. Spotlight Presentation. URL
Intensity-Free Learning of Temporal Point Processes.
ICLR 2020 - 8th International Conference on Learning Representations. Virtual, Apr 26-May 01, 2020. Spotlight Presentation. URL
2019
[4]
M. Biloš • B. Charpentier • S. Günnemann
Uncertainty on Asynchronous Time Event Prediction.
NeurIPS 2019 - 33rd Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 08-14, 2019. URL
Uncertainty on Asynchronous Time Event Prediction.
NeurIPS 2019 - 33rd Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 08-14, 2019. URL
[3]
A. Bojchevski • S. Günnemann
Certifiable Robustness to Graph Perturbations.
NeurIPS 2019 - 33rd Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 08-14, 2019. URL
Certifiable Robustness to Graph Perturbations.
NeurIPS 2019 - 33rd Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 08-14, 2019. URL
[2]
J. Gasteiger • S. Weißenberger • S. Günnemann
Diffusion Improves Graph Learning.
NeurIPS 2019 - 33rd Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 08-14, 2019. URL
Diffusion Improves Graph Learning.
NeurIPS 2019 - 33rd Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 08-14, 2019. URL
[1]
A. Bojchevski • S. Günnemann
Adversarial Attacks on Node Embeddings via Graph Poisoning.
ICML 2019 - 36th International Conference on Machine Learning. Long Beach, CA, USA, Jun 09-15, 2019. URL
Adversarial Attacks on Node Embeddings via Graph Poisoning.
ICML 2019 - 36th International Conference on Machine Learning. Long Beach, CA, USA, Jun 09-15, 2019. URL
©all images: LMU | TUM