Open topics for theses and practical courses

Unless otherwise specified, all topics are available as practical course (P1/P2), bachelor or master thesis.


Work group:


GPU based data mining on Android devices

Learning with Reduced Molecular Graphs

Oracle analysis of distant supervision errors

Weakly supervised discourse relation prediction

Incomplete Schema Relation Clustering

Weakly supervised learning with latent class predictions

Gradient matching for semi-supervised learning

Threshold-finding for knowledge-base completion using Gaussian processes

Path-based knowledge-base completion

Better sentence representations based on BERT

Explainable Policies for Game Play [Master Thesis]

Learning Composable Policies [Master Thesis]

The Cost of Feedback

Reinforcement Learning for Optimizing Electronic Circuit Design [Practical Course]

Algorithms for Finding Matched Molecular Pairs

2D pharmacophore descriptors for machine learning and similarity searches

Detecting errors in protein crystal structures

Molecular Puzzle

Causal inference for wind turbine extreme events [Bachelor or Master thesis]

Clustering of physiological, behavioral and climatic data of wild boars (Sus scrofa) [Bachelor or Master thesis]

Clustering of spatio-temporal climatological data [Master thesis]

Reinforcement Learning from Implicit and Explicit Feedback

Machine Learning for Personalized Education [Practical Course or Bachelor Thesis]

Probabilistic Models of Multimodal Distributions

Reward Inference for Sequential Decision Making from Diverse and Implicit Feedback [Master Thesis]

Imitation Learning Under Domain Mismatch

Selecting Sequences of Items for Non-monotone functions [Bachelor or Master Thesis]

Posterior Consistency in Partial Variational Autoencoders

Pharmacoinformatics Research Group [Practical Course]

Evaluation of different nowcasting techniques and data bases for temperature nowcasting

Exploratory Data Analysis on the GPU - Cuda Warp Level Primitives and Independent Thread Scheduling [Bachelor or Master Thesis]

Exploratory Data Analysis with Google TPU [Bachelor or Master Thesis]

Causal inference among climatological time series with extreme events [Master thesis]

Data Mining on Real World Accelerometer Time Series [Master thesis]

Implementation of Data Mining Approach for Short-range Temperature Forecasts

SIGMOD programming contest



  • Yigit Berkay Bozkurt, Bachelor Thesis: "Anomaly Detection by Heterogenous Graphical Granger Causality and its Application to Climate Data", 2019
  • Christina Pacher, Bachelor Thesis: "Clustering Weather Stations: A Clustering Application for Meteorological Data", summer term 2019
  • Thomas Spendlhofer, Bachelor Thesis: "Evaluating the usage of Tensor Processing Units (TPUs) for unsupervised learning on the example of the k-means algorithm", summer term 2019
  • Ernst Naschenweng, Bachelor Thesis: "A cache optimized implementation of the Floyd-Warshall Algorithm", summer term 2018
  • Hermann Hinterhauser, Bachelor Thesis: "ITGC: Information-theoretic grid-based clustering", summer term 2018, accepted paper in EDBT 2019 (download available here)
  • Mahmoud A. Ibrahim, Bachelor Thesis: "Parameter Free Mixed-Type Density-Based Clustering", winter term 2017/2018, accepted paper in DEXA 2018 (download available here)
  • Markus Tschlatscher: "Space-Filling Curves for Cache Efficient LU Decomposition", winter term 2017/18
  • Theresa Fruhwuerth, Master Thesis: "Uncovering High Resolution Mass Spectrometry Patterns through Audio Fingerprinting and Periodicity Mining Algorithms: An Exploratory Analysis", summer term 2017
  • Robert Fritze, PR1 "Combining spatial information and optimization for locating emergency medical service stations: A case study for Lower Austria", summer term 2017
  • Alexander Pfundner, PR2 "Integration of Density-based and Partitioning-based Clustering Methods", summer term 2017
  • Anton Kovác, Katerina Hlavácková-Schindler, Erasmus project, "Graphical Granger Causality for Detection Temporal Anomalies in EEG Data", winter term 2016/17 (download available here)