Bayesian (Deep) Learning / Uncertainty

Topics: Bayesian (Deep) Learning, Uncertainty, Probabilistic Models, (Implicit) Generative Models

Probabilistic modeling is a useful tool to analyze and understand real-world data, specifically enabling to represent the uncertainty inherent to the data and the learned model. In our research we study principle for (efficient) probabilisitc inference as well as applications of probabilistic models (often focusing on non-i.i.d. data scenarios). Specifically we also consider the combination of neural networks and Bayesian modelling -- often called "Bayesian Deep Learning" --, for example, by investigating principles for neural variational inference or deep generative models.

Selected Publications

  • Richard Kurle, Stephan Günnemann, Patrick van der Smagt
    Multi-Source Neural Variational Inference
    AAAI Conference on Artificial Intelligence, 2019
  • Subhabrata Mukherjee and Stephan Günnemann
    GhostLink: Latent Network Inference for Influence-aware Recommendation
    International World Wide Web Conference (WWW / TheWebConf), 2019
  • Aleksandar Bojchevski, Oleksandr Shchur, Daniel Zügner, Stephan Günnemann
    NetGAN: Generating Graphs via Random Walks
    International Conference on Machine Learning (ICML), 2018
  • Aleksandar Bojchevski, Stephan Günnemann
    Bayesian Robust Attributed Graph Clustering: Joint Learning of Partial Anomalies and Group Structure
    AAAI Conference on Artificial Intelligence, 2018
  • Dhivya Eswaran, Stephan Günnemann, Christos Faloutsos
    The Power of Certainty: A Dirichlet-Multinomial Model for Belief Propagation
    SIAM International Conference on Data Mining (SDM), 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)