Stephan Günnemann

Fellowship
Rudolf Mößbauer Tenure Track

Appointment
2016

Institution
Technical University of Munich

Department
Informatics

Focus Group
Data Mining & Analytics

Scientific Report on TUM-IAS Fellowship

The Focus Group Data Mining and Analytics studies principles for robust and trustworthy machine learning. Specifically, we are interested in learning principles for non-independent data such as graphs and temporal data. As the number of machine learning models deployed in the real world grows, questions regarding their robustness become increasingly important. Are the models’ predictions reliable or do they change if the underlying data gets slightly perturbed? In particular, for safety-critical and scientific use cases, it is essential to assess the models’ vulnerability to worst-case perturbations – ensuring that we can trust the machine learning model even in the worst case. full report …

Short CV

Stephan Günnemann acquired his doctoral degree in 2012 at RWTH Aachen University in the field of computer science. From 2012 to 2015 he was an associate of Carnegie Mellon University, USA; initially as a postdoctoral fellow and later as a senior researcher. Prof. Günnemann has been a visiting researcher at Simon Fraser University, Canada, and a research scientist at the Research & Technology Center of Siemens AG. In 2015, Prof. Günnemann set up an Emmy Noether research group at TUM Department of Informatics. He has been a professor at TUM since 2016.


Selected Awards

  • 2020, Google Faculty Research Award in Machine Learning
  • 2018, ACM SIGKDD Best Research Paper Award
  • 2017, Junior-Fellow of the German Computer Science Society
  • 2017, Microsoft Azure Research Award
  • 2015, Member of the Emmy Noether Program of the German Research Foundation (DFG)
  • 2013, Recipient of a German Academic Exchange Service (DAAD) Research Fellowship
  • 2013, Dissertation Award of the German Computer Science Society
  • 2013, Borchers Badge for Doctoral Dissertation, RWTH Aachen University
  • 2012, Recipient of a German Academic Exchange Service (DAAD) Research Fellowship
  • 2011, Best Paper Award at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases

Research Interest

Stephan Günnemann 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. Prof. Günnemann is particularly interested in studying machine learning methods targeting complex data domains such as graphs/networks and temporal data.


Selected Publications

  • Bojchevski A, Klicpera J, Günnemann S: "Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More". International Conference on Machine Learning. 2020.
     
  • Klicpera J, Weißenberger S, Günnemann S: "Diffusion improves graph learning". Advances in Neural Information Processing Systems. 2019; 13354-13366.
     
  • Bojchevski A, Günnemann S: "Certifiable Robustness to Graph Perturbations". Advances in Neural Information Processing Systems. 2019; 8319-8330.
     
  • Zügner D, Akbarnejad A, Günnemann S: "Adversarial Attacks on Neural Networks for Graph Data". ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2018: 2847-2856.
     
  • Bojchevski A, Shchur O, Zügner D, Günnemann S: "NetGAN: Generating Graphs via Random Walks". International Conference on Machine Learning. 2018; 609-618.

Publications as TUM-IAS-Fellow

2019

  • Aleksandar Bojchevski, Stephan Günnemann: Certifiable Robustness to Graph Perturbations. 2019 more… BibTeX
  • Daniel Zügner, Stephan Günnemann: Adversarial Attacks on Graph Neural Networks via Meta Learning. 2019 more… BibTeX
  • Johannes Klicpera, Stefan Weißenberger, Stephan Günnemann: Diffusion Improves Graph Learning. 2019 more… BibTeX
  • Kurle, Richard; Günnemann, Stephan; Van der Smagt, Patrick: Multi-Source Neural Variational Inference. Proceedings of the AAAI Conference on Artificial Intelligence 33, 2019, 4114-4121 more… BibTeX Full text ( DOI )
  • Marin Biloš, Bertrand Charpentier, Stephan Günnemann: Uncertainty on Asynchronous Time Event Prediction. 2019 more… BibTeX
  • Metzler, Saskia; Günnemann, Stephan; Miettinen, Pauli: Stability and dynamics of communities on online question–answer sites. Social Networks 58, 2019, 50-58 more… BibTeX Full text ( DOI )
  • Mrowca, Artur; Moser, Barbara; Günnemann, Stephan: Discovering Groups of Signals in In-Vehicle Network Traces for Redundancy Detection and Functional Grouping. In: Machine Learning and Knowledge Discovery in Databases. Springer International Publishing, 2019 more… BibTeX Full text ( DOI )
  • Mrowca, Artur; Nocker, Martin; Steinhorst, Sebastian; Günnemann, Stephan: Learning Temporal Specifications from Imperfect Traces Using Bayesian Inference. Proceedings of the 56th Annual Design Automation Conference 2019 on - DAC '19, ACM Press, 2019 more… BibTeX Full text ( DOI )
  • Mukherjee, Subhabrata; Guennemann, Stephan: GhostLink: Latent Network Inference for Influence-aware Recommendation. The World Wide Web Conference on - WWW '19, ACM Press, 2019 more… BibTeX Full text ( DOI )
  • Stephan Rabanser, Stephan Günnemann, Zachary C. Lipton: Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift. 2019 more… BibTeX
  • Zügner, Daniel; Akbarnejad, Amir; Günnemann, Stephan: Adversarial Attacks on Neural Networks for Graph Data. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, International Joint Conferences on Artificial Intelligence Organization, 2019 more… BibTeX Full text ( DOI )
  • Zügner, Daniel; Günnemann, Stephan: Certifiable Robustness and Robust Training for Graph Convolutional Networks. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '19, ACM Press, 2019 more… BibTeX Full text ( DOI )

2018

  • Bojchevski, Aleksandar; Günnemann, Stephan: Bayesian Robust Attributed Graph Clustering: Joint Learning of Partial Anomalies and Group Structure. AAAI Conference on Artificial Intelligence, 2018, 2738-2745 more… BibTeX
  • Bojchevski, Aleksandar; Günnemann, Stephan: Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking. International Conference on Learning Representations, 2018, 1–13 more… BibTeX
  • Bojchevski, Aleksandar; Shchur, Oleksandr; Zügner, Daniel; Günnemann,Stephan: NetGAN: Generating Graphs via Random Walks. International Conference on Machine Learning, 2018, 609–618 more… BibTeX
  • Klicpera, Johannes; Bojchevski, Aleksandar; Günnemann, Stephan: Predict then Propagate: Combining neural networks with personalized pagerank for classification on graphs. International Conference on Learning Representations, 2018 more… BibTeX
  • Kurle, Richard; Günnemann, Stephan; van der Smagt, Patrick: Multi-Source Neural Variational Inference. AAAI 2019, Association for the Advancement of Artificial Intelligence, 2018 more… BibTeX
  • Leibrandt, Richard; Günnemann, Stephan: Making Kernel Density Estimation Robust towards Missing Values in Highly Incomplete Multivariate Data without Imputation. In: Proceedings of the 2018 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics, 2018 more… BibTeX Full text ( DOI )
  • Shalaby, Marawan; Stutzki, Jan; Schubert, Matthias; Günnemann, Stephan: An LSTM Approach to Patent Classification based on Fixed Hierarchy Vectors. In: Proceedings of the 2018 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics, 2018 more… BibTeX Full text ( DOI )
  • Wolf, Peter; Mrowca, Artur; Nguyen, Tam Thanh; Baker, Bernard; Gunnemann, Stephan: Pre-ignition Detection Using Deep Neural Networks: A Step Towards Data-driven Automotive Diagnostics. 2018 21st International Conference on Intelligent Transportation Systems (ITSC), IEEE, 2018 more… BibTeX Full text ( DOI )
  • Zügner, Daniel; Akbarnejad, Amir; Günnemann, Stephan: Adversarial Attacks on Neural Networks for Graph Data. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18, ACM Press, 2018 more… BibTeX Full text ( DOI )
  • von Ritter, Lorenzo; Houle, Michael E.; Günnemann, Stephan: Intrinsic Degree: An Estimator of the Local Growth Rate in Graphs. In: Similarity Search and Applications. Springer International Publishing, 2018 more… BibTeX Full text ( DOI )

2017

  • A. Bojchevski, and S. Günnemann: Bayesian robust attributed graph clustering: joint learning of partial anomalies and group structure,. AAAI Conf. Artificial Intelligence, 2017 more… BibTeX
  • Bojchevski, Aleksandar; Matkovic, Yves; Günnemann, Stephan: Robust Spectral Clustering for Noisy Data. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '17, ACM Press, 2017 more… BibTeX Full text ( DOI )
  • Eswaran, Dhivya; Günnemann, Stephan; Faloutsos, Christos: The Power of Certainty: A Dirichlet-Multinomial Model for Belief Propagation. In: Proceedings of the 2017 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics, 2017 more… BibTeX Full text ( DOI )
  • Eswaran, Dhivya; Günnemann, Stephan; Faloutsos, Christos; Makhija, Disha; Kumar, Mohit: ZooBP. Proceedings of the VLDB Endowment 10 (5), 2017, 625-636 more… BibTeX Full text ( DOI )
  • Günnemann, Stephan: Machine Learning Meets Databases. Datenbank-Spektrum 17 (1), 2017, 77-83 more… BibTeX Full text ( DOI )
  • Hubig, Nina; Fengler, Philip; Züfle, Andreas; Yang, Ruixin; Günnemann, Stephan: Detection and Prediction of Natural Hazards Using Large-Scale Environmental Data. In: Advances in Spatial and Temporal Databases. Springer International Publishing, 2017 more… BibTeX Full text ( DOI )
  • M. Then, S. Günnemann, A. Kemper, and T. Neumann: Efficient batched distance and centrality computation in unweighted and weighted graphs. Conference on Database Systems for Business, Technology, and Web, 2017 more… BibTeX
  • Passing, Linnea; Then, Manuel; Hubig, Nina; Lang, Harald; Schreier, Michael; Günnemann, Stephan; Kemper, Alfons; Neumann, Thomas: SQL- and Operator-centric Data Analytics in Relational Main-Memory Databases. 2017, 10.5441/002/edbt.2017.09(other entry) more… BibTeX Full text ( DOI )
  • Then, Manuel; Günnemann, Stephan; Kemper, Alfons; Neumann, Thomas: Efficient Batched Distance, Closeness and Betweenness Centrality Computation in Unweighted and Weighted Graphs. Datenbank-Spektrum 17 (2), 2017, 169-182 more… BibTeX Full text ( DOI )
  • Then, Manuel; Kersten, Timo; Günnemann, Stephan; Kemper, Alfons; Neumann, Thomas: Automatic algorithm transformation for efficient multi-snapshot analytics on temporal graphs. Proceedings of the VLDB Endowment 10 (8), 2017, 877-888 more… BibTeX Full text ( DOI )

2016

  • Boden, Brigitte; Günnemann, Stephan; Hoffmann, Holger; Seidl, Thomas: MiMAG: mining coherent subgraphs in multi-layer graphs with edge labels. Knowledge and Information Systems 50 (2), 2016, 417-446 more… BibTeX Full text ( DOI )