News
-
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…
-
MLG Workshop at ECML/PKDD
–
We are happy to announce, that the 22nd Mining and Learning with Graphs workshop will be held at ECML/PKDD on September 15th 2025 in Porto! We will have exciting keynotes by Rebekka Burgholz and Matthias Fey, as well as plenty of time for socializing. Submit your work until 14th of June at http://mlg-europe.github.io! The European…
-
Paper accepted at ICML 2025
–
We’re thrilled to share that our paper “Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win” by Lorenz Kummer, Samir Moustafa, Anatol Ehrlich, Franka Bause, Nikolaus Suess, Wilfried Gansterer and Nils Kriege has been accpted at the 42nd International Conference on Machine Learning, July 13th-19th 2025, Vancouver, Canada! This work bridges two important areas…
-
Lorenz presents at AISTATS 2025
–
Further raising awareness for the inherent vulnerabilities of Graph Neural Networks (GNNs) to adversarial Bit Flip Attacks (BFAs), Lorenz presented our group’s latest work “On the Relationship Between Robustness and Expressivity of Graph Neural Networks” by Lorenz Kummer, Wilfried Gansterer and Nils Kriege at the 28th International Conference on Artificial Intelligence and Statistics (AISTATS). In…
-
Lorenz presents at AAAI 2025
–
With “Crossfire: An Elastic Defense Framework for Graph Neural Networks under Bit Flip Attacks” by Lorenz Kummer, Samir Moustafa, Wilfried Gansterer and Nils Kriege, we presented a novel approach to defending Graph Neural Networks (GNNs) from Bit Flip Attacks (BFAs) at the 39th Annual AAAI Conference on Artificial Intelligence. Crossfire combines innovative techniques like saliency-based…
-
Paper Accepted at AISTATS 2025
–
We are glad to announce our paper “On the Relationship Between Robustness and Expressivity of Graph Neural Networks” by Lorenz Kummer, Wilfried Gansterer and Nils Kriege has been accepted at the 28th International Conference on Artificial Intelligence and Statistics (AISTATS) , which will take place from 3rd – May 5th, 2025 in Mai Kaho, Thailand!…
-
Paper Accepted at TMLR 2025
–
We are excited to announce that the paper Maximally Expressive GNNs for Outerplanar Graphs by Franka Bause, Fabian Jogl, Patrick Indri, Tamara Drucks, David Penz, Nils Kriege, Thomas Gärtner, Pascal Welke, and Maximilian Thiessen has been accepted to Transactions on Machine Learning Research (TMLR)! The paper proposes a linear time graph transformation that enables the…
-
Paper Accepted at AAAI 2025
–
We are excited to announce the acceptance of our recent work “Crossfire: An Elastic Defense Framework for Graph Neural Networks under Bit Flip Attacks” by Lorenz Kummer, Samir Moustafa, Wilfried Gansterer and Nils Kriege at the 39th Annual AAAI Conference on Artificial Intelligence, which will take place in Philadelphia, Pennsylvania, USA from February 25 –…
-
Paper Accepted at LoG 2024
–
The paper “Preventing Representation Rank Collapse in MPNNs by Splitting the Computational Graph” was accepted at the Learning on Graphs Conference (LoG) 2024!