Publikationen

2024

  • Marten Lienen, David Lüdke, Jan Hansen-Palmus, Stephan Günnemann
    From Zero to Turbulence: Generative Modeling for 3D Flow Simulation
    International Conference on Learning Representations (ICLR), 2024
    [Paper] [Code]

2023

  • Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann
    Hierarchical Randomized Smoothing
    Conference on Neural Information Processing Systems (NeurIPS), 2023
  • Jan Schuchardt, Yan Scholten, Stephan Günnemann
    Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
    Conference on Neural Information Processing Systems (NeurIPS), 2023
  • Lukas Gosch, Simon Geisler, Daniel Sturm, Bertrand Charpentier, Daniel Zügner, Stephan Günnemann
    Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
    Conference on Neural Information Processing Systems (NeurIPS), 2023
  • David Lüdke, Marin Biloš, Oleksandr Shchur, Marten Lienen, Stephan Günnemann
    Add and Thin: Diffusion for Temporal Point Processes
    Conference on Neural Information Processing Systems (NeurIPS), 2023
  • Filippo Guerranti, Zinuo Yi, Anna Starovoit, Rafiq Kamel, Simon Geisler, Stephan Günnemann
    On the Adversarial Robustness of Graph Contrastive Learning Methods
    New Frontiers in Graph Learning Workshop (GLFrontiers), NeurIPS 2023
  • Aman Saxena*, Tom Wollschläger*, Nicola Franco, Jeanette Miriam Lorenz and Stephan Günnemann
    Randomized Smoothing-Inspired Quantum Encoding Schemes With Formal Robustness Guarantees
    Quantum Techniques in Machine Learning 2023
  • Nicola Franco, Tom Wollschläger, Benedikt Poggel, Stephan Günnemann and Jeanette Miriam Lorenz
    Efficient MILP Decomposition in Quantum Computing for ReLU Network Robustness
    Quantum Computing and Engineering 2023
  • Tong Zhao, Wei Jin, Yozen Liu, Yingheng Wang, Gang Liu, Stephan Günneman, Neil Shah, and Meng Jiang
    Graph Data Augmentation for Graph Machine Learning: A Survey
    June edition of the IEEE Data Engineering Bulletin, Vol. 47 No. 2, 2023
  • Francesco Campi, Lukas Gosch, Tom Wollschläger, Yan Scholten, Stephan Günnemann
    Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness
    Workshop on New Frontiers in Adversarial Machine Learning, ICML 2023
  • Felippe Schmoeller Roza, Karsten Roscher, Stephan Günnemann
    Safe and Efficient Operation with Constrained Hierarchical Reinforcement Learning
    European Workshop on Reinforcement Learning (EWRL 2023)
  • Jonathan Külz, Andreas Spitz, Ahmad Abu-Akel, Stephan Günnemann, Robert West
    United States politicians’ tone became more negative with 2016 primary campaigns
    Scientific Reports, 2023
  • Jianxiang Feng, Matan Atad, Ismael Rodríguez, Maximilian Durner, Stephan Günnemann, Rudolph Triebel
    Density-based Feasibility Learning with Normalizing Flows for Introspective Robotic Assembly
    Workshop on Robotics and AI: The Future of Industrial Assembly Tasks, Robotics: Science and Systems (RSS) 2023
  • Simon Geisler, Yujia Li, Daniel Mankowitz, Ali Taylan Cemgil, Stephan Günnemann, Cosmin Paduraru
    Transformers Meet Directed Graphs
    International Conference on Machine Learning (ICML), 2023
  • Nicholas Gao, Stephan Günnemann
    Generalizing Neural Wave Functions
    International Conference on Machine Learning (ICML), 2023
    [Paper] [Project Page]
  • Marin Biloš, Kashif Rasul, Anderson Schneider, Yuriy Nevmyvaka, Stephan Günnemann
    Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion
    International Conference on Machine Learning (ICML), 2023
  • Tom Wollschläger, Nicholas Gao, Bertrand Charpentier, Mohamed Amine Ketata, Stephan Günnemann
    Uncertainty Estimation for Molecules: Desiderata and Methods
    International Conference on Machine Learning (ICML), 2023
  • Arthur Kosmala, Johannes Gasteiger, Nicholas Gao, Stephan Günnemann
    Ewald-based Long-Range Message Passing for Molecular Graphs
    International Conference on Machine Learning (ICML), 2023
    [Paper] [Project Page]
  • Nicola Franco, Daniel Korth, Jeanette Miriam Lorenz, Karsten Roscher, Stephan Günnemann
    Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection
    (best paper award)

    In AISafety & SafeRL Joint Workshop at IJCAI, 2023
  • Jonas Gregor Wiese, Lisa Wimmer, Theodore Papamarkou, Bernd Bischl, Stephan Günnemann, David Rügamer
    Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry
    (best paper award)
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2023
  • Jan Schuchardt, Tom Wollschläger, Aleksandar Bojchevski, Stephan Günnemann
    Localized Randomized Smoothing for Collective Robustness Certification
    International Conference on Learning Representations (ICLR), 2023
    (selected for spotlight presentation)
    [Paper] [Project Page]
  • Nicholas Gao, Stephan Günnemann
    Sampling-free Inference for Ab-Initio Potential Energy Surface Networks
    International Conference on Learning Representations (ICLR), 2023
    [Paper] [Project Page]
  • Lukas Gosch, Daniel Sturm, Simon Geisler, Stephan Günnemann
    Revisiting Robustness in Graph Machine Learning
    International Conference on Learning Representations (ICLR), 2023
    [Paper] [Project Page]
  • Raffaele Paolino, Aleksandar Bojchevski, Stephan Günnemann, Gitta Kutyniok, Ron Levie
    Unveiling the sampling density in non-uniform geometric graphs
    International Conference on Learning Representations (ICLR), 2023

2022

  • Nicola Franco, Tom Wollschläger, Nicholas Gao, Jeanette Miriam Lorenz, and Stephan Günnemann
    Quantum Robustness Verification: A Hybrid Quantum-Classical Neural Network Certification Algorithm
    In IEEE International Conference on Quantum Computing and Engineering (QCE), 2022.
  • Alexandru Mara, Jefrey Lijffijt, Stephan Günnemann, Tijl De Bie
    A Systematic Evaluation of Node Embedding Robustness
    Learning on Graphs Conference (LOG), 2022
  • Johannes Gasteiger, Chendi Qian, Stephan Günnemann
    Influence-Based Mini-Batching for Graph Neural Networks
    Learning on Graphs Conference (LOG), 2022
  • Richard Leibrandt, Stephan Günnemann
    Generalized Density Attractor Clustering for Incomplete Data
    Journal track of the ECML PKDD, to appear in a special issue of the Springer journal "Data Mining and Knowledge Discovery", 2022
  • Jan Schuchardt, Stephan Günnemann
    Invariance-Aware Randomized Smoothing Certificates
    Neural Information Processing Systems (NeurIPS), 2022
    [Paper] [Project Page]
  • Yan Scholten, Jan Schuchardt, Simon Geisler, Aleksandar Bojchevski, Stephan Günnemann
    Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
    Neural Information Processing Systems (NeurIPS), 2022
  • Felix Mujkanovic, Simon Geisler, Aleksandar Bojchevski, Stephan Günnemann
    Are Defenses for Graph Neural Networks Robust?
    Neural Information Processing Systems (NeurIPS), 2022
  • Leon Hetzel, Simon Boehm, Niki Kilbertus, Stephan Günnemann, Mohammad Lotfollahi, Fabian J Theis
    Predicting Single-Cell Perturbation Responses for Unseen Drugs
    Neural Information Processing Systems (NeurIPS), 2022
  • Marten Lienen, Stephan Günnemann
    torchode: A Parallel ODE Solver for PyTorch
    The Symbiosis of Deep Learning and Differential Equations II, NeurIPS (2022)
    [Paper] [GitHub]
  • Morgane Ayle, Jan Schuchardt, Lukas Gosch, Daniel Zügner, Stephan Günnemann
    Training Differentially Private Graph Neural Networks with Random Walk Sampling
    Trustworthy and Socially Responsible Machine Learning (TSRML), NeurIPS (2022)
  • Lukas Gosch, Daniel Sturm, Simon Geisler, Stephan Günnemann
    Revisiting Robustness in Graph Machine Learning
    Trustworthy and Socially Responsible Machine Learning (TSRML), NeurIPS (2022)
    & NeurIPS ML Safety Workshop (2022)
  • Sina Stocker, Johannes Gasteiger, Florian Becker, Stephan Günnemann, Johannes T. Margraf
    How Robust are Modern Graph Neural Network Potentials in Long and Hot Molecular Dynamics Simulations?
    Machine Learning: Science and Technology, 2022
  • Johannes Gasteiger, Muhammed Shuaibi, Anuroop Sriram, Stephan Günnemann, Zachary Ward Ulissi, C. Lawrence Zitnick, Abhishek Das
    GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets
    Transactions on Machine Learning Research, 2022
    [Paper]
  • Felippe Schmoeller Roza, Hassan Rasheed, Karsten Roscher, Xiangyu Ning, Stephan Günnemann
    Safe Robot Navigation Using Constrained Hierarchical Reinforcement Learning 
    IEEE 2022 International Conference on Machine Learning and Applications
  • Armin Moin, Moharram Challenger, Atta Badii, and Stephan Günnemann
    Towards Model-Driven Engineering for Quantum AI
    GI Quantum Computing Workshop - INFORMATIK 2022
    [Paper]
  • John Rachwan, Daniel Zügner, Bertrand Charpentier, Simon Geisler, Morgane Ayle, Stephan Günnemann
    Winning the Lottery Ahead of Time: Efficient Early Network Pruning
    International Conference on Machine Learning (ICML), 2022
  • Peter Súkeník, Aleksei Kuvshinov, Stephan Günnemann
    Intriguing Properties of Input-Dependent Randomized Smoothing
    International Conference on Machine Learning (ICML), 2022
  • Hannes Stärk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan Günnemann, Pietro Lió
    3D Infomax improves GNNs for Molecular Property Prediction
    International Conference on Machine Learning (ICML), 2022
  • Marin Biloš, Andrei Smirdin, Stephan Günnemann
    Modeling Solutions to Ordinary and Partial Differential Equations with Continuous Initial Value Networks
    ICML Workshop on Continuous Time Methods for Machine Learning, 2022
  • Marin Biloš, Emanuel Ramneantu, Stephan Günnemann
    Irregularly-Sampled Time Series Modeling with Spline Networks
    ICML Workshop on Continuous Time Methods for Machine Learning, 2022
  • Armin Moin, Moharram Challenger, Atta Badii, Stephan Günnemann
    Supporting AI Engineering on the IoT Edge through Model-Driven TinyML
    IEEE COMPSAC SETA (Software Engineering Technology and Applications) 2022
    [Paper]
  • Poulami Sinhamahapatra, Rajat Koner, Karsten Roscher, Stephan Günnemann:
    Is it all a cluster game? Exploring Out-of-Distribution Detection based on Clustering in the Embedding Space
    SafeAI@AAAI 2022
  • Codrut-Andrei Diaconu, Sudipan Saha, Stephan Günnemann, Xiaoxiang Zhu
    Understanding the Role of Weather Data for Earth Surface Forecasting using a ConvLSTM-based Model
    EarthVision 2022
  • Jonathan Külz, Andreas Spitz, Ahmad Abu-Akel, Stephan Günnemann, Robert West
    United States Politicians' Tone Became More Negative with 2016 Primary Campaigns
    International Conference on Computational Social Science (IC2S2), 2022
  • Armin Moin, Andrei Mituca, Moharram Challenger, Atta Badii, Stephan Günnemann
    ML-Quadrat & DriotData: A Model-Driven Engineering Tool and a Low-Code Platform for Smart IoT Services
    IEEE/ACM International Conference on Software Engineering (ICSE) 2022 - Demonstrations
    [Paper]
  • Aleksei Kuvshinov, Stephan Günnemann
    Robustness Verification of ReLU Networks via Quadratic Programming
    Machine Learning (2022)
  • Nicholas Gao, Stephan Günnemann
    Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions
    International Conference on Learning Representations (ICLR), 2022
    [Paper | GitHub]
  • Marten Lienen, Stephan Günnemann
    Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks
    International Conference on Learning Representations (ICLR), 2022
  • Bertrand Charpentier, Simon Kibler, Stephan Günnemann
    Differentiable DAG Sampling
    International Conference on Learning Representations (ICLR), 2022
    [Paper | Github]
  • Daniel Zügner, Bertrand Charpentier, Morgane Ayle, Sascha Geringer, Stephan Günnemann 
    End-to-End Learning of Probabilistic Hierarchies on Graphs 
    International Conference on Learning Representations (ICLR), 2022
    [Paper | GitHub | Slides | BibTeX ]
  • Simon Geisler, Johanna Sommer, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann
    Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
    International Conference on Learning Representations (ICLR), 2022
    [Paper]
  • Bertrand Charpentier, Oliver Borchert, Daniel Zügner, Simon Geisler, Stephan Günnemann 
    Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions
    International Conference on Learning Representations (ICLR), 2022
    [Paper | Github]
  • Aleksei Kuvshinov, Daniel Knobloch, Daniel Külzer, Elen Vardanyan, Stephan Günnemann
    Domain Reconstruction for UWB Car Key Localization Using Generative Adversarial Networks
    Thirty-Fourth Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-22)
  • Stephan Günnemann
    Graph Neural Networks: Adversarial Robustness
    Graph Neural Networks: Foundations, Frontiers, and Applications, Springer, 2022
    (Invited book chapter)
    [Book chapter | References]
  • Armin Moin, Moharram Challenger, Atta Badii, Stephan Günnemann
    A Model-Driven Approach to Machine Learning and Software Modeling for the IoT
    International Journal on Software and Systems Modeling (SoSyM), 2022
    [Paper]

2021

  • Simon Geisler, Tobias Schmidt, Hakan Şirin, Daniel Zügner, Aleksandar Bojchevski, Stephan Günnemann
    Robustness of Graph Neural Networks at Scale
    Neural Information Processing Systems (NeurIPS), 2021
    [Paper | GitHub ]
  • Johannes Gasteiger, Florian Becker, Stephan Günnemann
    GemNet: Universal Directional Graph Neural Networks for Molecules
    Neural Information Processing Systems (NeurIPS), 2021
    [Paper | GitHub (PyTorch) | GitHub (TensorFlow)]
  • Maximilian Stadler, Bertrand Charpentier, Simon Geisler, Daniel Zügner, Stephan Günnemann
    Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
    Neural Information Processing Systems (NeurIPS), 2021
    [Paper|Github]
  • Marin Biloš, Johanna Sommer, Syama Sundar Rangapuram, Tim Januschowski, Stephan Günnemann
    Neural Flows: Efficient Alternative to Neural ODEs
    Neural Information Processing Systems (NeurIPS), 2021
    [Paper | Code]
  • Johannes Gasteiger, Chandan Yeshwanth, Stephan Günnemann
    Directional Message Passing on Molecular Graphs via Synthetic Coordinates
    Neural Information Processing Systems (NeurIPS), 2021
    [Paper | GitHub]
  • Oleksandr Shchur, Ali Caner Turkmen, Tim Januschowski, Jan Gasthaus, Stephan Günnemann
    Detecting Anomalous Event Sequences with Temporal Point Processes
    Neural Information Processing Systems (NeurIPS), 2021
    [Paper]
  • Johannes C. Paetzold, Julian McGinnis, Suprosanna Shit, Ivan Ezhov, Paul Büschl, Chinmay Prabhakar, Anjany Sekuboyina, Mihail Todorov, Georgios Kaissis, Ali Ertürk, Stephan Günnemann, Björn Menze
    Whole Brain Vessel Graphs: A Dataset and Benchmark for Graph Learning and Neuroscience
    NeurIPS 2021 Datasets and Benchmarks Track, 2021
    [Paper]
  • Hannes Stärk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan Günnemann, Pietro Lio
    3D Infomax improves GNNs for Molecular Property Prediction
    AI for Science Workshop & Self-Supervised Learning Workshop, NeurIPS, 2021
  • Artur Mrowca, Florian Gyrock, Stephan Günnemann
    Temporal State Change Bayesian Networks for Modeling of Evolving Multivariate State Sequences
    Data Mining and Knowledge Discovery (DAMI), 2021
    [Paper]
  • Sven Elflein, Bertrand Charpentier, Daniel Zügner, Stephan Günnemann
    On Out-of-distribution Detection with Energy-Based Models
    Uncertainty and Robustness in Deep Learning Workshop, ICML, 2021
    [Paper|Github]
  • Oleksandr Shchur, Ali Caner Türkmen, Tim Januschowski, Jan Gasthaus, Stephan Günnemann
    Detecting Anomalous Event Sequences with Temporal Point Processes
    Uncertainty and Robustness in Deep Learning Workshop, ICML, 2021
  • Daniel Zügner, Francois-Xavier Aubet, Victor Garcia Satorras, Tim Januschowski, Stephan Günnemann, Jan Gasthaus
    A Study of Joint Graph Inference and Forecasting
    Time Series Workshop, ICML, 2021
    [Paper]
  • Sebastian Bischoff, Stephan Günnemann, Martin Jaggi, Sebastian Stich
    On Second-order Optimization Methods for Federated Learning
    Beyond First Order Methods in Machine Learning Systems Workshop, ICML, 2021
    [Paper]
  • Johannes Gasteiger, Marten Lienen, Stephan Günnemann
    Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More
    International Conference on Machine Learning (ICML), 2021
    [Paper | PosterLCN GitHub | GTN GitHub]
  • Anna-Kathrin Kopetzki, Bertrand Charpentier, Daniel Zügner, Sandhya Giri, Stephan Günnemann
    Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
    International Conference on Machine Learning (ICML), 2021
    [Paper|Github]
  • Marin Biloš, Stephan Günnemann
    Scalable Normalizing Flows for Permutation Invariant Densities
    International Conference on Machine Learning (ICML), 2021
    [Paper]
  • Anna-Kathrin Kopetzki, Stephan Günnemann
    Reachable sets of classifiers and regression models: (non-)robustness analysis and robust training
    Machine Learning Journal, 2021
    [Paper]
  • Oleksandr Shchur, Ali Caner Türkmen, Tim Januschowski, Stephan Günnemann
    Neural Temporal Point Processes: A Review
    International Joint Conference on Artificial Intelligence (IJCAI), 2021
    [Paper]
  • Tom Haider, Felippe Schmoeller Roza, Dirk Eilers, Karsten Roscher, Stephan Günnemann
    Domain Shifts in Reinforcement Learning: Identifying Disturbances in Environments
    AISafety Workshop, IJCAI, 2021
    [Paper]
  • Rajat Koner, Hang Li, Marcel Hildebrandt, Deepan Das, Volker Tresp, Stephan Günnemann
    Graphhopper: Multi-Hop Scene Graph Reasoning for Visual Question Answering
    International Semantic Web Conference (ISWC), 2021
    [Paper]
  • Kevin Kennard Thiel, Florian Naumann, Eduard Jundt, Stephan Günnemann, Gudrun Klinker
    C.DOT - Convolutional Deep Object Tracker for Augmented Reality Based Purely on Synthetic Data
    IEEE Transactions on Visualization and Computer Graphics (TVCG), 2021
    [Paper]
  • Leon Hetzel, David S. Fischer, Stephan Günnemann, Fabian J. Theis
    Graph Representation Learning for Single Cell Biology
    Current Opinion in Systems Biology, 2021
    [Paper]
  • Jan Schuchardt, Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann
    Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks
    International Conference on Learning Representations (ICLR), 2021
    [Paper | GitHub | Poster | Slides ]
  • Daniel Zügner, Tobias Kirschstein, Michele Catasta, Jure Leskovec, Stephan Günnemann
    Language-Agnostic Representation Learning of Source Code from Structure and Context
    International Conference on Learning Representations (ICLR), 2021
    [Paper | Poster | Slides | Code | Live Demo]
  • Yihan Wu, Aleksandar Bojchevski, Aleksei Kuvshinov, Stephan Günnemann
    Completing the Picture: Randomized Smoothing Suffers from Curse of Dimensionality for a Large Family of Distributions
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
    [Paper | GitHub]
  • Martin Atzmüller, Stephan Günnemann, Albrecht Zimmermann
    Mining communities and their descriptions on attributed graphs: a survey
    Data Mining and Knowledge Discovery (DAMI), 2021
    [Paper]
  • Maximilian E. Schüle, Harald Lang, Maximilian Springer, Alfons Kemper, Thomas Neumann, Stephan Günnemann
    In-Database Machine Learning with SQL on GPUs
    International Conference on Scientific and Statistical Database Management (SSDBM), 2021
    [Paper]
  • Maria Kaiser, Stephan Günnemann, Markus Disse
    Spatiotemporal analysis of heavy rain-induced flood occurrences in Germany using a novel event database approach
    Journal of Hydrology, 2021
    [Paper]

2020

  • Oleksandr Shchur, Nicholas Gao, Marin Biloš, Stephan Günnemann
    Fast and Flexible Temporal Point Processes with Triangular Maps
    (selected for oral presentation)
    Neural Information Processing Systems (NeurIPS), 2020
    [Paper | Code + Data | Video + Slides  | Poster ]
  • Bertrand Charpentier, Daniel Zügner, Stephan Günnemann
    Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
    Neural Information Processing Systems (NeurIPS), 2020
    [Paper|Video|Github]
  • Simon Geisler, Daniel Zügner, Stephan Günnemann
    Reliable Graph Neural Networks via Robust Aggregation
    Neural Information Processing Systems (NeurIPS), 2020
    [Paper | GitHub | Video (Slideslive)Google Colab Notebook]
  • Richard Kurle, Syama Sundar Rangapuram, Emmanuel de Bézenac, Stephan Günnemann, Jan Gasthaus
    Deep Rao-Blackwellised Particle Filters for Time Series Forecasting
    Neural Information Processing Systems (NeurIPS), 2020
    [Paper]
  • Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann
    Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More
    International Conference on Machine Learning (ICML), 2020
    [Paper]
  • Daniel Zügner, Stephan Günnemann
    Certifiable Robustness of Graph Convolutional Networks under Structure Perturbations
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020
    [Paper | GitHub | Slides (KDD 2020)BibTeX ]
  • Aleksandar Bojchevski*, Johannes Gasteiger*, Bryan Perozzi, Amol Kapoor, Martin Blais, Benedek Rozemberczki, Michal Lukasik, Stephan Günnemann
    Scaling Graph Neural Networks with Approximate PageRank
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020
    [Paper | Code | Colab | Supplementary material]
  • Richard Leibrandt, Stephan Günnemann
    Gauss Shift: Density Attractor Clustering Faster than Mean Shift
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2020
  • Armin Moin, Stephan Rössler, Marouane Sayih, Stephan Günnemann
    From Things’ Modeling Language (ThingML) to Things’ Machine Learning (ThingML2)
    ACM / IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS), 2020
  • Daniel Zügner, Oliver Borchert, Amir Akbarnejad, Stephan Günnemann
    Adversarial Attacks on Graph Neural Networks: Perturbations and their Patterns
    ACM Transactions on Knowledge Discovery from Data, 2020
  • Johannes Gasteiger, Janek Groß, Stephan Günnemann
    Directional Message Passing for Molecular Graphs
    (selected for spotlight presentation)
    International Conference on Learning Representations (ICLR), 2020
    [Paper | Code | Supplementary material]
  • Oleksandr Shchur, Marin Biloš, Stephan Günnemann
    Intensity-Free Learning of Temporal Point Processes
    (selected for spotlight presentation) 
    International Conference on Learning Representations (ICLR), 2020
  • Richard Kurle, Botond Cseke, Alexej Klushyn, Patrick van der Smagt, Stephan Günnemann
    Continual Learning with Bayesian Neural Networks for Non-Stationary Data
    International Conference on Learning Representations (ICLR), 2020
  • Zhen Han, Yuyi Wang, Yunpu Ma, Stephan Günnemann, Volker Tresp
    Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs
    (nominated for best paper)
    Conference on Automated Knowledge Base Construction (AKBC), 2020
  • Eugenio Angriman, Alexander van der Grinten, Aleksandar Bojchevski, Daniel Zügner, Stephan Günnemann, Henning Meyerhenke
    Group Centrality Maximization for Large-scale Graphs
    SIAM Symposium on Algorithm Engineering and Experiments (ALENEX), 2020
    [PDF
  • Maria Kaiser, Stephan Günnemann, Markus Disse
    Providing Guidance on Efficient Flash Flood Documentation: an Application Based Approach
    Journal of Hydrology
  • Johannes Gasteiger, Shankari Giri, Johannes T. Margraf, Stephan Günnemann
    Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules
    Workshop on Machine Learning for Molecules, NeurIPS 2020
  • Felippe Schmoeller Roza, Maximilian Henne, Karsten Roscher, Stephan Günnemann
    Assessing different box merging strategies and uncertainty estimation methods in multimodel object detection
    Beyond mAP: Reassessing the Evaluation of Object Detectors, Workshop at ECCV 2020
  • Nick Harmening, Marin Bilos, Stephan Günnemann
    Deep Representation Learning and Clustering of Traffic Scenarios
    (best paper award)

    Workshop on AI for Autonomous Driving, ICML 2020
  • Marcel Hildebrandt, Hang Li, Rajat Koner, Volker Tresp, Stephan Günnemann

    Scene Graph Reasoning for Visual Question Answering
    Workshop on Graph Representation Learning and Beyond, ICML 2020

2019

  • Marin Biloš, Bertrand Charpentier, Stephan Günnemann
    Uncertainty on Asynchronous Time Event Prediction
    (selected for spotlight presentation) 
    Neural Information Processing Systems (NeurIPS), 2019
    [PDF| Supplementary material]
  • Aleksandar Bojchevski, Stephan Günnemann
    Certifiable Robustness to Graph Perturbations
    Neural Information Processing Systems (NeurIPS), 2019
    [PDF | Code | Supplementary material]
  • Johannes Gasteiger, Stefan Weißenberger, Stephan Günnemann
    Diffusion Improves Graph Learning
    Neural Information Processing Systems (NeurIPS), 2019
    [PDF | Code | Supplementary material]
  • Stephan Rabanser, Stephan Günnemann, Zachary Lipton
    Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
    Neural Information Processing Systems (NeurIPS), 2019
  • Daniel Zügner, Stephan Günnemann
    Certifiable Robustness and Robust Training for Graph Convolutional Networks
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2019
    [PDF]
  • Aleksandar Bojchevski, Stephan Günnemann
    Adversarial Attacks on Node Embeddings via Graph Poisoning
    International Conference on Machine Learning (ICML), 2019
    [PDF | Code | Supplementary Material]
  • Daniel Zügner, Stephan Günnemann
    Adversarial Attacks on Graph Neural Networks via Meta Learning
    International Conference on Learning Representations (ICLR), 2019
  • Johannes Gasteiger, Aleksandar Bojchevski, Stephan Günnemann
    Predict then Propagate: Graph Neural Networks meet Personalized PageRank
    International Conference on Learning Representations (ICLR), 2019
    [PDF | Code | Supplementary material]
  • Subhabrata Mukherjee and Stephan Günnemann
    GhostLink: Latent Network Inference for Influence-aware Recommendation 
    International World Wide Web Conference (WWW / TheWebConf), 2019
  • Richard Kurle, Stephan Günnemann, Patrick van der Smagt
    Multi-Source Neural Variational Inference
    AAAI Conference on Artificial Intelligence, 2019
    [PDF]
  • Artur Mrowca, Martin Nocker, Sebastian Steinhorst, Stephan Günnemann
    Learning Temporal Specifications from Imperfect Traces Using Bayesian Inference
    Design Automation Conference (DAC), 2019
  • Saskia Metzler, Stephan Günnemann, Pauli Miettinen
    Stability and Dynamics of Communities on Online Question-Answer Sites
    Social Networks, pp. 50-58, 2019
    [PDF]
  • Aleksandar Bojchevski, Johannes Klicpera, Bryan Perozzi, Martin Blais, Amol Kapoor, Michal Lukasik, Stephan Günnemann
    Is PageRank All You Need for Scalable Graph Neural Networks?
    Workshop on Mining and Learning with Graphs (MLG), KDD 2019
  • Oleksandr Shchur, Stephan Günnemann
    Overlapping Community Detection with Graph Neural Networks
    Workshop on Deep Learning on Graphs, KDD 2019
  • Stephan Rabanser, Stephan Günnemann, Zachary Lipton
    Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
    Workshop on Debugging Machine Learning Models, ICLR 2019
    [Extended Version]
  • Federico Monti, Oleksandr Shchur, Aleksandar Bojchevski, Or Litany, Stephan Günnemann, Michael M. Bronstein
    Dual-Primal Graph Convolutional Networks
    Workshop on Graph Embedding and Mining, ECML-PKDD 2019
    [PDF]
  • Maximilian Schüle, Matthias Bungeroth, Alfons Kemper, Stephan Günnemann, Thomas Neumann
    MLearn: A Declarative Machine Learning Language for Database Systems
    Workshop on Data Management for End-to-End Machine Learning, SIGMOD 2019
  • Maximilian Schüle, Frédéric Simonis, Thomas Heyenbrock, Alfons Kemper, Stephan Günnemann, Thomas Neumann
    In-Database Machine Learning: Gradient Descent and Tensor Algebra for Main Memory Database Systems
    GI Conference on Database Systems for Business, Technology, and the Web (BTW), 2019
  • Maximilian Schüle, Matthias Bungeroth, Dimitri Vorona, Alfons Kemper, Stephan Günnemann, Thomas Neumann
    ML2SQL - Compiling a Declarative Machine Learning Language to SQL and Python
    International Conference on Extending Database Technology (EDBT), 2019
  • Maximilian Schüle, Dimitri Vorona, Linnea Passing, Harald Lang, Alfons Kemper, Stephan Günnemann, Thomas Neumann
    The Power of SQL Lambda Functions
    International Conference on Extending Database Technology (EDBT), 2019
  • Daniel Zügner, Amir Akbarnejad, Stephan Günnemann
    Adversarial Attacks on Neural Networks for Graph Data (Extended Abstract)
    International Joint Conference on Artificial Intelligence (IJCAI), 2019
    (Invited contribution to the IJCAI Sister Conference Best Paper Track)

2018

  • Oleksandr Shchur, Maximilian Mumme, Aleksandar Bojchevski, Stephan Günnemann
    Pitfalls of Graph Neural Network Evaluation
    Relational Representation Learning Workshop, NIPS 2018
    [PDF]
  • Aleksandar Bojchevski, Oleksandr Shchur, Daniel Zügner, Stephan Günnemann
    NetGAN: Generating Graphs via Random Walks
    International Conference on Machine Learning (ICML), 2018
    [PDF | Supplementary material]
  • Daniel Zügner, Amir Akbarnejad, Stephan Günnemann
    Adversarial Attacks on Neural Networks for Graph Data 
    (Best Research Paper Award)
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2018
    [PDF]
  • Artur Mrowca, Barbara Moser, Stephan Günnemann
    Discovering Groups of Signals in In-Vehicle Network Traces for Redundancy Detection and Functional Grouping
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2018 
  • Lorenzo von Ritter, Michael E. Houle, Stephan Günnemann
    Intrinsic Degree: An Estimator of the Local Growth Rate in Graphs
    International Conference on Similarity Search and Applications (SISAP), 2018
  • Aleksandar Bojchevski, Stephan Günnemann
    Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking 
    International Conference on Learning Representations (ICLR), 2018
    [PDF | Supplementary material]
  • Richard Leibrandt, Stephan Günnemann
    Making Kernel Density Estimation Robust towards Missing Values in Highly Incomplete Multivariate Data without Imputation
    SIAM International Conference on Data Mining (SDM), 2018 
  • Marawan Shalaby, Jan Stutzki, Matthias Schubert, Stephan Günnemann
    An LSTM approach to Patent Classification based on Fixed Hierarchy Vectors
    SIAM International Conference on Data Mining (SDM), 2018 
  • Aleksandar Bojchevski, Stephan Günnemann
    Bayesian Robust Attributed Graph Clustering: Joint Learning of Partial Anomalies and Group Structure
    AAAI Conference on Artificial Intelligence, pp. 2738-2745, 2018
    [PDF | Supplementary material]
  • Peter Wolf, Artur Mrowca, Tam Thanh Nguyen, Bernard Bäker, Stephan Günnemann
    Pre-ignition Detection Using Deep Neural Networks: A Step Towards Data-driven Automotive Diagnostics
    IEEE International Conference on Intelligent Transportation Systems (ITSC), 2018
  • Oleksandr Shchur, Aleksandar Bojchevski, Mohamed Farghal, Stephan Günnemann, Yusuf Saber
    Anomaly Detection in Car-Booking Graphs
    IEEE International Conference on Data Mining Workshops (ICDMW), 2018
  • Armin Moin, Stephan Rössler, Stephan Günnemann
    ThingML+: Augmenting Model-Driven Software Engineering for the Internet of Things with Machine Learning
    Workshop on Model-Driven Engineering for IoT, International Conference on Model Driven Engineering Languages and Systems, 2018

2017

  • Aleksandar Bojchevski, Yves Matkovic, Stephan Günnemann
    Robust Spectral Clustering for Noisy Data: Modeling Sparse Corruptions Improves Latent Embeddings
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 737-746, 2017
    [PDFSupplementary Material]
  • Dhivya Eswaran, Stephan Günnemann, Christos Faloutsos
    The Power of Certainty: A Dirichlet-Multinomial Model for Belief Propagation
    SIAM International Conference on Data Mining (SDM), pp. 144-152, 2017
  • Dhivya Eswaran, Stephan Günnemann, Christos Faloutsos, Disha Makhija, Mohit Kumar
    ZooBP: Belief Propagation for Heterogeneous Networks
    International Conference on Very Large Data Bases, PVLDB 10(5): 625-636 (2017)
    [PDF]
  • Manuel Then, Timo Kersten, Stephan Günnemann, Alfons Kemper, Thomas Neumann
    Automatic Algorithm Transformation for Efficient Multi-Snapshot Analytics on Temporal Graphs
    International Conference on Very Large Data Bases, PVLDB 10(8): 877-888 (2017)
  • Nina Hubig, Philip Fengler, Andreas Züfle, Ruixin Yang, Stephan Günnemann
    Detection and Prediction of Natural Hazards using Large-Scale Environmental Data
    International Symposium on Spatial and Temporal Databases (SSTD), pp. 300-316, 2017 
  • Brigitte Boden, Stephan Günnemann, Holger Hoffmann, Thomas Seidl
    MiMAG: Mining Coherent Subgraphs in Multi-Layer Graphs with Edge Labels
    Knowledge and Information Systems (KAIS), pp. 417-446, 2017
    [Supplementary material]
  • Linnea Passing, Manuel Then, Nina Hubig, Harald Lang, Michael Schreier, Stephan Günnemann, Alfons Kemper, Thomas Neumann
    SQL- and Operator-centric Data Analytics in Relational Main-Memory Databases
    International Conference on Extending Database Technology (EDBT), pp. 84-95, 2017
  • Manuel Then, Stephan Günnemann, Alfons Kemper, Thomas Neumann 
    Efficient Batched Distance, Closeness and Betweenness Centrality Computation in Unweighted and Weighted Graphs
    Datenbank-Spektrum, 17(2): 169-182 (2017)
  • Manuel Then, Stephan Günnemann, Alfons Kemper, Thomas Neumann
    Efficient Batched Distance and Centrality Computation in Unweighted and Weighted Graphs
    GI Conference on Database Systems for Business, Technology, and the Web (BTW), pp. 247-266, 2017
  • Stephan Günnemann
    Machine Learning Meets Databases
    Datenbank-Spektrum, pp. 77-83, 2017, invited paper
    [PDF]

2017 - Preprints

  • Stephan Rabanser, Oleksandr Shchur, Stephan Günnemann
    Introduction to Tensor Decompositions and their Applications in Machine Learning 
    [PDF]

2016

  • Saskia Metzler, Stephan Günnemann, Pauli Miettinen
    Hyperbolae Are No Hyperbole: Modelling Communities That Are Not Cliques
    IEEE International Conference on Data Mining (ICDM), pp. 330-339, 2016.
  • Neil Shah, Alex Beutel, Bryan Hooi, Leman Akoglu, Stephan Günnemann, Disha Makhija, Mohit Kumar, Christos Faloutsos,
    EdgeCentric: Anomaly Detection in Edge-Attributed Networks
    IEEE
    International Conference on Data Mining Workshops (ICDMW), pp. 327-334, 2016.
  • Subhabrata Mukherjee, Stephan Günnemann, Gerhard Weikum
    Continuous Experience-aware Language Model
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 1075-1084, 2016.
  • Bryan Hooi, Neil Shah, Alex Beutel, Stephan Günnemann, Leman Akoglu, Mohit Kumar, Disha Makhija, Christos Faloutsos
    BIRDNEST: Bayesian Inference for Ratings-Fraud Detection
    SIAM
    International Conference on Data Mining (SDM), pp. 495-503, 2016.
  • Miguel Araujo, Stephan Günnemann, Spiros Papadimitriou, Christos Faloutsos, Prithwish Basu, Ananthram Swami, Evangelos Papalexakis and Danai Koutra
    Discovery of ‘comet’ communities in temporal and labeled graphs (Com2)
    Knowledge and Information Systems (KAIS), pp. 657-677, 2016

2015

  • Tobias Kötter, Stephan Günnemann, Christos Faloutsos, and Michael R. Berthold
    Automatic taxonomy extraction from bipartite graphs
    (Invitation to special issue: ICDM Best papers)

    IEEE International Conference on Data Mining (ICDM), pages 221–230, 2015.
  • Wolfgang Gatterbauer, Stephan Günnemann, Danai Koutra, Christos Faloutsos
    Linearized and Single-Pass Belief Propagation
    PVLDB, Vol. 8(5), pp. 581-592, 2015
  • Tobias Kötter, Stephan Günnemann, Michael Berthold, and Christos Faloutsos
    Extracting Taxonomies from Bipartite Graphs
    International World Wide Web Conference (WWW), pp. 51-52, 2015
  • Jay-Yoon Lee, Manzil Zaheer, Stephan Günnemann, Alexander J. Smola
    Preferential Attachment in Graphs with Affinities
    International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 571-580, 2015
  • Manuel Then, Linnea Passing, Nina Hubig, Stephan Günnemann, Alfons Kemper, and Thomas Neumann
    Effiziente Integration von Data- und Graph-Mining-Algorithmen in relationale Datenbanksysteme 
    LWA 2015, Special interest group database systems, pages 45–49, 2015.
  • Emmanuel Müller, Ira Assent, Stephan Günnemann, Thomas Seidl, Jennifer Dy
    Editorial: MultiClust Special Issue on Discovering, Summarizing and Using Multiple Clusterings
    Machine Learning Journal (MLJ), Vol. 98(1-2), pp. 1-5, 2015
    [PDF]

2014

  • Miguel Araujo, Stephan Günnemann, Gonzalo Mateos and Christos Faloutsos
    Beyond Blocks: Hyperbolic Community Detection
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), pp. 50-65, 2014
    [PDF], [Supplementary material]
  • Stephan Günnemann, Nikou Günnemann and Christos Faloutsos
    Detecting Anomalies in Dynamic Rating Data: A Robust Probabilistic Model for Rating Evolution
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 841-850, 2014
    [PDF]
  • Stephan Günnemann, Ines Färber, Matthias Rüdiger and Thomas Seidl
    SMVC: Semi-Supervised Multi-View Clustering in Subspace Projections
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 253-262, 2014
    [PDF], [Supplementary material]
  • Nikou Günnemann, Stephan Günnemann and Christos Faloutsos
    Robust Multivariate Autoregression for Anomaly Detection in Dynamic Product Ratings
    International World Wide Web Conference (WWW), pp. 361-372, 2014
    [PDF]
  • Tobias Kötter, Stephan Günnemann, Christos Faloutsos and Michael BertholdFault-tolerant Concept Detection in Information Networks
    Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 410-421, 2014
    [PDF], [Supplementary material]
  • Miguel Araujo, Spiros Papadimitriou, Stephan Günnemann, Christos Faloutsos, Prithwish Basu, Ananthram Swami, Evangelos Papalexakis and Danai Koutra
    Com2: Fast Automatic Discovery of Temporal (‘Comet’) Communities
    (Best Student Paper Runner-Up Award)

    Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 271-283, 2014
    [PDF], [Supplementary material]
  • Stephan Günnemann, Ines Färber, Brigitte Boden and Thomas Seidl
    GAMer: A Synthesis of Subspace Clustering and Dense Subgraph Mining
    Knowledge and Information Systems (KAIS), Vol. 40(2), pp. 243-278, 2014
    [PDF], [Supplementary material]

2013

  • Stephan Günnemann and Christos Faloutsos
    Mixed Membership Subspace Clustering
    IEEE International Conference on Data Mining (ICDM), 2013
    [PDF], [Supplementary material], [KDnuggets news]
  • Stephan Günnemann, Ines Färber, Sebastian Raubach and Thomas Seidl
    Spectral Subspace Clustering for Graphs with Feature Vectors
    IEEE International Conference on Data Mining (ICDM), 2013
    [PDF], [Supplementary material]
  • Hardy Kremer, Stephan Günnemann, Arne Held and Thomas SeidlAn Evaluation Framework for Temporal Subspace Clustering ApproachesIEEE International Conference on Data Mining Workshops (ICDMW), 2013
    [PDF], [Download page]
  • Brigitte Boden, Stephan Günnemann, Holger Hoffmann and Thomas Seidl
    RMiCS: A Robust Approach for Mining Coherent Subgraphs in Edge-Labeled Multi-Layer Graphs
    International Conference on Scientific and Statistical Database Management (SSDBM), 2013
    [PDF]
  • Hardy Kremer, Stephan Günnemann, Simon Wollwage and Thomas Seidl
    Nesting the Earth Mover’s Distance for Effective Cluster Tracing
    International Conference on Scientific and Statistical Database Management (SSDBM), 2013
    [PDF]
  • Stephan Günnemann, Brigitte Boden, Ines Färber and Thomas Seidl
    Efficient Mining of Combined Subspace and Subgraph Clusters in Graphs with Feature Vectors
    Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 261-275, 2013
    [PDF], [Supplementary material]
  • Stephan GünnemannSubspace Clustering for Complex Data
    GI Conference on Database Systems for Business, Technology, and the Web (BTW), pp. 343-362, 2013
    [PDF]
  • Jennifer H. Nguyen, Bo Hu, Stephan Günnemann and Martin Ester
    Finding Contexts of Social Influence in Online Social Networks
    (Student paper award)
    7th Workshop on Social Network Mining and Analysis at ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2013
    [PDF]
  • Geng Li, Stephan Günnemann and Mohammed J. Zaki
    Stochastic Subspace Search for Top-K Multi-View Clustering
    4th MultiClust Workshop on Multiple Clusterings, Multi-view Data, and Multi-source Knowledge-driven Clustering at ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2013
    [PDF]

2012

  • Stephan Günnemann, Phuong Dao, Mohsen Jamali and Martin Ester
    Assessing the Significance of Data Mining Results on Graphs with Feature Vectors
    (Invitation to special issue: ICDM Best papers)
    Proc. IEEE International Conference on Data Mining (ICDM 2012), Brussels, Belgium, 2012
    [PDF]
  • Hardy Kremer, Stephan Günnemann, Arne Held and Thomas Seidl
    Effective and Robust Mining of Temporal Subspace Clusters
    Proc. IEEE International Conference on Data Mining (ICDM 2012), Brussels, Belgium, 2012[PDF]
  • Stephan Günnemann, Ines Färber and Thomas Seidl
    Multi-View Clustering Using Mixture Models in Subspace Projections
    Proc. of the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD 2012), Beijing, China, 2012
    [PDF], [Supplementary material]
  • Stephan Günnemann, Ines Färber, Kittipat Virochsiri and Thomas Seidl
    Subspace Correlation Clustering: Finding Locally Correlated Dimensions in Subspace Projections of the Data
    Proc. of the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD 2012), Beijing, China, 2012
    [PDF]
  • Brigitte Boden, Stephan Günnemann, Holger Hoffmann and Thomas Seidl
    Mining Coherent Subgraphs in Multi-Layer Graphs with Edge Labels
    Proc. of the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD 2012), Beijing, China, 2012
    [PDF], [Supplementary material]
  • Stephan Günnemann, Brigitte Boden and Thomas Seidl
    Finding Density-Based Subspace Clusters in Graphs with Feature Vectors
    Data Mining and Knowledge Discovery Journal (DMKD), Vol. 25, Nr. 2, pp. 243-269, 2012
    [PDF], [Supplementary material]
  • Stephan Günnemann, Hardy Kremer, Charlotte Laufkötter and Thomas Seidl
    Tracing Evolving Subspace Clusters in Temporal Climate Data
    Data Mining and Knowledge Discovery (DMKD), Vol. 24(2), pp. 387-410, 2012
    [PDF]
  • Brigitte Boden, Stephan Günnemann and Thomas Seidl
    Tracing Clusters in Evolving Graphs with Node Attributes
    Proceedings of The 21st ACM Conference on Information and Knowledge Management (CIKM 2012), Maui, USA , 2012
    [PDF]
  • Hardy Kremer, Stephan Günnemann, Arne Held and Thomas Seidl
    Mining of Temporal Coherent Subspace Clusters in Multivariate Time Series Databases
    Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 444-455, 2012
    [PDF]
  • Stephan Günnemann, Brigitte Boden and Thomas Seidl
    Substructure Clustering: A Novel Mining Paradigm for Arbitrary Data Types
    Proc. of the 24th International Conference on Scientific and Statistical Database Management (SSDBM 2012), Chania, Greece, 2012
    [PDF]
  • Stephan Günnemann
    Subspace Clustering for Complex Data
    Dissertation, Fakultät für Mathematik, Informatik und Naturwissenschaften, RWTH Aachen University., 2012
    [PDF]
  • Stephan Günnemann, Hardy Kremer, Richard Musiol, Roman Haag and Thomas Seidl
    A Subspace Clustering Extension for the KNIME Data Mining Framework
    Proc. IEEE International Conference on Data Mining (ICDM 2012), Brussels, Belgium, 2012[PDF], [Download page]
  • Emmanuel Müller, Stephan Günnemann, Ines Färber and Thomas Seidl
    Discovering Multiple Clustering Solutions: Grouping Objects in Different Views of the Data
    Tutorial at IEEE 28th International Conference on Data Engineering (ICDE), 2012[PDF]
  • Emmanuel Müller, Stephan Günnemann, Ines Färber and Thomas Seidl
    Discovering Multiple Clustering Solutions: Grouping Objects in Different Views of the Data
    Tutorial at the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2012

2011

  • Stephan Günnemann, Emmanuel Müller, Sebastian Raubach and Thomas Seidl
    Flexible Fault Tolerant Subspace Clustering for Data with Missing Values
    IEEE International Conference on Data Mining (ICDM), pp. 231-240, 2011[PDF], [Supplementary material]
  • Stephan Günnemann, Brigitte Boden and Thomas Seidl
    DB-CSC: A density-based approach for subspace clustering in graphs with feature vectors
    (Best paper award)

    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), pp. 565-580, 2011[PDF], [Supplementary material], [Extended version]
  • Stephan Günnemann, Ines Färber, Emmanuel Müller, Ira Assent and Thomas Seidl
    External Evaluation Measures for Subspace Clustering
    ACM Conference on Information and Knowledge Management (CIKM), pp. 1363-1372, 2011[PDF]
  • Emmanuel Müller, Ira Assent, Stephan Günnemann and Thomas Seidl
    Scalable Density-Based Subspace Clustering
    ACM Conference on Information and Knowledge Management (CIKM), pp. 1077-1086, 2011[PDF]
  • Stephan Günnemann, Hardy Kremer, Charlotte Laufkötter and Thomas Seidl
    Tracing Evolving Clusters by Subspace and Value Similarity
    Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 444-456, 2011[PDF]
  • Stephan Günnemann, Hardy Kremer, Dominik Lenhard and Thomas SeidlSubspace Clustering for Indexing High Dimensional Data: A Main Memory Index based on Local Reductions and Individual Multi-RepresentationsInternational Conference on Extending Database Technology (EDBT), pp. 237-248, 2011[PDF]
  • Hardy Kremer, Stephan Günnemann, Anca Maria Ivanescu, Ira Assent and Thomas SeidlEfficient Processing of Multiple DTW Queries in Time Series DatabasesInternational Conference on Scientific and Statistical Database Management (SSDBM), pp. 150-167, 2011[PDF]
  • Emmanuel Müller, Ira Assent, Stephan Günnemann, Patrick Gerwert, Matthias Hannen, Timm Jansen and Thomas SeidlA Framework for Evaluation and Exploration of Clustering Algorithms in Subspaces of High Dimensional DatabasesGI Conference on Database Systems for Business, Technology, and the Web (BTW), pp. 347-366, 2011[PDF]
  • Stephan Günnemann, Hardy Kremer and Thomas SeidlAn Extension of the PMML Standard to Subspace Clustering ModelsWorkshop on Predictive Model Markup Language at ACM Conference on Knowledge Discovery and Data Mining (SIGKDD), pp. 48-53, 2011[PDF]
  • Emmanuel Müller, Stephan Günnemann, Ira Assent and Thomas SeidlProceedings of the 2nd MultiClust Workshop: Discovering, Summarizing and Using Multiple ClusteringsCEUR Workshop Proceedings , 2011[Proceedings]
  • Emmanuel Müller, Stephan Günnemann, Ines Färber and Thomas SeidlDiscovering Multiple Clustering Solutions: Grouping Objects in Different Views of the DataTutorial at SIAM International Conference on Data Mining (SDM), 2011
    [PDF]

2010

  • Stephan Günnemann, Ines Färber, Brigitte Boden and Thomas SeidlSubspace Clustering Meets Dense Subgraph Mining: A Synthesis of Two ParadigmsIEEE International Conference on Data Mining (ICDM), pp. 845-850, 2010[PDF], [Extended Version], [Supplementary material]
  • Stephan Günnemann, Hardy Kremer and Thomas SeidlSubspace Clustering for Uncertain DataSIAM International Conference on Data Mining (SDM), pp. 385-396, 2010[PDF], [Supplementary material]
  • Stephan Günnemann and Thomas SeidlSubgraph Mining on Directed and Weighted GraphsPacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 133-146, 2010[PDF]
  • Philipp Kranen, Stephan Günnemann, Fries, S. and Thomas SeidlMC-Tree: Improving Bayesian Anytime ClassificationInternational Conference on Scientific and Statistical Database Management (SSDBM), pp. 252-269, 2010[PDF]
  • Stephan Günnemann, Ines Färber, Hardy Kremer and Thomas SeidlCoDA: Interactive Cluster Based Concept DiscoveryPVLDB, Vol. 3(2), pp. 1633-1636, 2010[PDF]
  • Ira Assent, Hardy Kremer, Stephan Günnemann and Thomas SeidlPattern detector: fast detection of suspicious stream patterns for immediate reactionInternational Conference on Extending Database Technology (EDBT), pp. 709-712, 2010[PDF]
  • Stephan Günnemann, Ines Färber, Emmanuel Müller and Thomas SeidlASCLU: Alternative Subspace ClusteringInternational Workshop on Discovering, Summarizing and Using Multiple Clusterings at ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2010[PDF]
  • Ira Assent, Emmanuel Müller, Stephan Günnemann, Ralph Krieger and Thomas SeidlLess is More: Non-Redundant Subspace ClusteringInternational Workshop on Discovering, Summarizing and Using Multiple Clusterings at ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2010[PDF]
  • Ines Färber, Stephan Günnemann, Hans-Peter Kriegel, Peer Kröger, Emmanuel Müller, Erich Schubert, Thomas Seidl and Arthur ZimekOn Using Class-Labels in Evaluation of ClusteringsInternational Workshop on Discovering, Summarizing and Using Multiple Clusterings at ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2010[PDF]
  • Stephan Günnemann, Hardy Kremer, Ines Färber and Thomas SeidlMCExplorer: Interactive Exploration of Multiple (Subspace) Clustering SolutionsIEEE International Conference on Data Mining Workshops (ICDMW), pp. 1387-1390, 2010[PDF]
  • Hardy Kremer, Stephan Günnemann and Thomas SeidlDetecting Climate Change in Multivariate Time Series Data by Novel Clustering and Cluster Tracing TechniquesIEEE International Conference on Data Mining Workshops (ICDMW), pp. 96-97, 2010[PDF]
  • Emmanuel Müller, Stephan Günnemann, Ines Färber and Thomas SeidlDiscovering Multiple Clustering Solutions: Grouping Objects in Different Views of the DataTutorial at IEEE International Conference on Data Mining (ICDM), pp. 1220, 2010[PDF]

2009

  • Stephan Günnemann, Emmanuel Müller, Ines Färber and Thomas Seidl
    Detection of orthogonal concepts in subspaces of high dimensional data
    ACM Conference on Information and Knowledge Management (CIKM), pp. 1317-1326, 2009[PDF]
  • Emmanuel Müller, Ira Assent, Stephan Günnemann, Ralph Krieger and Thomas SeidlRelevant Subspace Clustering: Mining the Most Interesting Non-redundant Concepts in High Dimensional DataIEEE International Conference on Data Mining (ICDM), pp. 377-386, 2009[PDF], [Supplementary material]
  • Emmanuel Müller, Ira Assent, Ralph Krieger, Stephan Günnemann and Thomas SeidlDensEst: Density Estimation for Data Mining in High Dimensional SpacesSIAM International Conference on Data Mining (SDM), pp. 173-184, 2009[PDF]
  • Emmanuel Müller, Stephan Günnemann, Ira Assent and Thomas SeidlEvaluating Clustering in Subspace Projections of High Dimensional DataPVLDB, Vol. 2(1), pp. 1270-1281, 2009[PDF], [Supplementary material]
  • Ira Assent, Stephan Günnemann, Hardy Kremer and Thomas Seidl
    High-Dimensional Indexing for Multimedia Features
    GI Conference on Database Systems for Business, Technology, and the Web (BTW), pp. 187-206, 2009
    [PDF]
  • Emmanuel Müller, Ira Assent, Stephan Günnemann, Timm Jansen and Thomas Seidl
    OpenSubspace: An Open Source Framework for Evaluation and Exploration of Subspace Clustering Algorithms in WEKA
    Open Source in Data Mining Workshop at Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 2-13, 2009
    [PDF]