We have 4 papers accepted at NeurIPS 2019, including one spotlight presentation! Uncertainty on Asynchronous Event Prediction (spotlight) Bertrand Charpentier, Marin Biloš, Stephan GünnemannCertifiable Robustness to Graph PerturbationsAleksandar Bojchevski, Stephan...
I am happy to present our research results on adversarial robustness of machine learning methods for graphs as a keynote speaker at multiple events ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Workshop on Learning and Mining for Cybersecurity,...
Acceptance rate for oral papers: 9% Overall acceptance rate: 14%
Paper (+ long oral presentation) on Graph Adversarial Attacks for Node Embeddings accepted at ICML 2019
Our work "Adversarial Attacks on Node Embeddings" has been accepted at the International Conference on Machine Learning, ICML 2019.
Our work "GhostLink: Mining Latent Influence Networks for Influence-aware Item Recommendation", where we tackle the problem of learning latent influence networks (i.e. an instance of graph inference), has been accepted at the International World Wide Web...
We have two papers accepted at the International Conference on Learning Representations (ICLR): "Adversarial Attacks on Graph Neural Networks via Meta Learning" and "Predict then Propagate: Graph Neural Networks meet Personalized PageRank"....
Our group has won the Best Research Paper award at KDD 2018 for the work "Adversarial Attacks on Neural Networks for Graph Data". The paper studies for the first time adversarial attacks to graphs, specifically focusing on state-of-the-art graph convolutional...
Our work on implicit generative models for graphs "NetGAN: Generating Graphs via Random Walks" has been accepted as a long/oral paper at ICML 2018! Congratulations to my co-authors Aleksandar Bojchevski, Oleksandr Shchur, and Daniel Zügner!
Our paper "Adversarial Attacks on Neural Networks for Graph Data" has been accepted as an oral/long paper at KDD 2018! In our paper we study the novel problem of adversarial machine learning for graphs, specifically considering state-of-the-art node classification...
Our paper "Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking" has been accepted at the International Conference on Learning Representations (ICLR).
Our papers "An LSTM approach to Patent Classification based on Fixed Hierarchy Vectors" and "Making Kernel Density Estimation Robust towards Missing Values in Highly Incomplete Multivariate Data without Imputation" have been accepted at the SIAM International...
Our paper "Bayesian Robust Attributed Graph Clustering: Joint Learning of Partial Anomalies and Group Structure" has been accepted at AAAI 2018.
We are currently offering student assistant positions (Hiwi/Tutor) for our lecture on Machine Learning. More details are available here.
The German Computer Science Society (Gesellschaft für Informatik, GI) has awarded a Junior-Fellowship to Prof. Dr. Stephan Günnemann. The fellowship is designated to early-career scientists for their excellent contribution to the field of computer science. Official...
Our paper "Robust Spectral Clustering for Noisy Data" has been accepted at KDD 2017. Congratulations to my co-authors Aleksandar Bojchevski and Yves Matkovic!
Our paper "Detection and Prediction of Natural Hazards using Large-Scale Environmental Data" has been accepted at SSTD 2017. Congratulations to all co-authors!
Our paper "Automatic Algorithm Transformation for Efficient Multi-Snapshot Analytics on Temporal Graphs" has been accepted at VLDB 2017. Congratulations to all co-authors!
Our group has received a Microsoft Azure Research Award from Microsoft Research!
Our paper "The Power of Certainty: A Dirichlet-Multinomial Model for Belief Propagation" has been accepted at the SIAM International Conference on Data Mining (SDM 2017). Congratulations to all my co-authors!
We are currently offering student assistant positions (Hiwi/Tutor) for our lecture on Mining Massive Datasets. More details are available here.
Our paper "ZooBP: Belief Propagation for Heterogeneous Networks" has been accepted at the International Conference on Very Large Data Bases (VLDB 2017). Congratulations to all my co-authors!
Stephan Günnemann will give a presentation at the Berlin Big Data Center (TU Berlin, DFKI) on November 28, 2016. The title of the talk is "Beyond Independence: Efficient Learning Techniques for Networks and Temporal Data".
Our paper “SQL- and Operator-centric Data Analytics in Relational Main-Memory Databases ” has been accepted at the International Conference on Extending Database Technology (EDBT 2017). Congratulations to all my co-authors!
Our paper “Hyperbolae Are No Hyperbole: Modelling Communities That Are Not Cliques” has been accepted as a full paper at the IEEE International Conference on Data Mining (ICDM 2016). Congratulations to my co-authors Saskia Metzler and Pauli Miettinen! Our paper “EdgeCentric:...
Our paper “Continuous Experience-aware Language Model” has been accepted at the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) as a full paper + oral presentation. The acceptance rate was 8.9%.
Stephan Günnemann serves as co-chair of the organization committee of the 2017 International Conference on Very Large Data Bases (VLDB).
Our paper “MiMAG: Mining Coherent Subgraphs in Multi-Layer Graphs with Edge Labels” has been accepted at the Knowledge and Information Systems journal.
Stephan Günnemann has been invited as a speaker at the annual meeting of the “GI-Beirat der Universitätsprofessoren” (GIBU 2016).