Andreas Roth
Forschungsthemen
- Wissensgewinnung aus graph-strukturierten Daten
- Expressivität von tiefen Graph Neuronalen Netzen
- Wissenstransfer zur Kompression von Modellen
Ausgewählte Publikationen
2024
- A. Roth, F. Bause, N. M. Kriege, and T. Liebig, “Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph,” in Learning on Graphs Conference, 2024. PMLR. (LoG 2024)
2023
- A. Roth and T. Liebig, “Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks,” in Learning on Graphs Conference (pp. 35-1), 2023. PMLR. (LoG 2023)
- A. Roth and T. Liebig, “Distilling Influences to Mitigate Prediction Churn in Graph Neural Networks,” in Asian Conference on Machine Learning (pp. 1151-1166), 2023. PMLR. (ACML 2023)
2022
- A. Roth and T. Liebig, “Transforming PageRank into an Infinite-Depth Graph Neural Network,” in Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2022. (ECML PKDD 2022, Best Paper Award)
2021
- A. Roth, K. Wüstefeld, and F. Weichert. “A Data-Centric Augmentation Approach for Disturbed Sensor Image Segmentation,” in Journal of Imaging, vol. 7, iss. 10, 2021. (Journal of Imaging)
Auszeichnungen
- Best Paper Award, ECML PKDD 2022.
- Top Reviewer, NeurIPS 2024.
Andere Wissenschaftliche Aktivitäten
- Program Committee member, Workshop on Mining and Learning with Graphs, ECML-PKDD 2024
- Reviewer: NeurIPS 2024, Log 2024, ICLR 2025, Machine Learning Journal