Author: Anatol Ehrlich
-
Franka Receives the Award of Excellence – National Prize for the Best Dissertations
Congratulations to Franka on her excellent dissertation “Efficient and Expressive Graph Learning” and for receiving the award! The “Award of Excellence” is given by the Austrian Ministry of Women, Science and Research (Bundesministerium Frauen, Wissenschaft und Forschung), to the best 40 dissertations of the last year. Dr.techn. Franka Bause, BSc MSc completed her Bachelor’s and…
-
Group Excursion to AKW Zwentendorf
On Friday the 24th October 2025, the KriegeGroup set out to explore the Nuclear Reactor Facilities in Zwentendorf (Lower Austria). The Zwentendorf Nuclear Power Plant was a fully built 700 MW boiling-water reactor near Vienna, completed in 1978 but never put into operation. On November 5, 1978, a referendum resulted in a narrow majority (50.47%)…
-
Franka Successfully Defends Thesis
On Thursday, 7th of August, Franka successfully defended her doctoral thesis entitled “Efficient and Expressive Graph Learning”. Congratulations Franka!!
-
“Best of the Best”-Award for Franka
We are happy to announce that Franka was honored in the category Publications in highest ranking venues 2024 (Gruppe PraeDoc). The award recognizes outstanding research contributions by PhD students from the faculty of computer science.
-
Anatol Presents Poster at 13th ICCS
Anatol Presents his poster titled “Bio-Isostere Guided Molecular Property Prediction” at the 13th International Conference on Chemical Structures in Noordwijkerhout, The Netherlands. The poster proposes a novel idea to pre-train a GNN by creating bio-isosteres from a large unlabeled dataset. These bio-isosteres are dynamically sampled during training to form triplets, where the anchor and positive…
-
Group Excursion to Mödling
Last week, the Kriegegroup went on an excursion to the beautiful hilltops of Mödling in Lower Austria. After arriving at the central station, Charlotte led us to the Bergruine Mödling, followed by a steep ascent to the Husar Temple, where we took the image below. Finally we ended up at the excellent Heuriger called Pferschy-Seper…
-
Investigating the Loss Landscape of Graph Neural Networks
Graph neural networks (GNNs) have emerged as powerful tools for learning from graph-structured data, with applications spanning multiple domains. Despite their widespread use, understanding their internal mechanics remains challenging, especially how optimization, expressivity, and generalization are interrelated. In response, the project aims to investigate the loss landscape of GNNs to gain insights into the optimization…
-
Your Own Idea!
Do you have a specific project in mind you want to investigate, that is not already listed on the thesis page? Then you can contact Prof. Nils Kriege to propose your own project idea! Your project idea must fulfill the following requirements: Requirements: Strong interest in graph learning. Contact: Nils Kriege
-
Kriege Group Website Goes Online!
The kriegegroup.univie.ac.at website has officially launched on 11th November 2024. Its aim is to consolidate the information about the Machine Learning with Graphs work group to make our research more accessible to interested individuals. For the more tech savvy people, here is a quick overview of the tech stack used on this website: WordPress as…
-
Latex Example Post
At first, we sample $f(x)$ in the $N$ ($N$ is odd) equidistant points around $x^*$:\[f_k = f(x_k),\: x_k = x^*+kh,\: k=-\frac{N-1}{2},\dots,\frac{N-1}{2}\] where $h$ is some step.Then we interpolate points ${(x_k,f_k)}$ by polynomial\begin{equation} \label{eq:poly} P_{N-1}(x)=\sum_{j=0}^{N-1}{a_jx^j}\end{equation} Its coefficients ${a_j}$ are found as a solution of system of linear equations:\begin{equation} \label{eq:sys} \left{ P_{N-1}(x_k) = f_k\right},\quad k=-\frac{N-1}{2},\dots,\frac{N-1}{2}\end{equation} Here are…