Publications

2025

Evaluating Spatiotemporal Prediction Models in Low-Data Regime Preprint

Identifying Axiomatic Mathematical Transformation Steps using Tree-Structured Pointer Networks Sebastian Wankerl, Jan Pfister, Andrzej Dulny, Gerhard Götz, Andreas Hotho Transactions on Machine Learning Research (TMLR) OpenReview

BibTeX

@article{wankerl2025identifying,
  title   = {Identifying Axiomatic Mathematical Transformation Steps using Tree-Structured Pointer Networks},
  author  = {Wankerl, Sebastian and Pfister, Jan and Dulny, Andrzej and G{\"o}tz, Gerhard and Hotho, Andreas},
  journal = {Transactions on Machine Learning Research},
  year    = {2025}
}

Physical Knowledge Improves Prediction of EM Fields Andrzej Dulny, Farzad Jabbarigargari, Andreas Hotho, Laura Maria Schreiber, Maxim Terekhov, Anna Krause arXiv preprint arXiv

BibTeX

@article{dulny2025physical,
  title   = {Physical Knowledge Improves Prediction of EM Fields},
  author  = {Dulny, Andrzej and Jabbarigargari, Farzad and Hotho, Andreas and Schreiber, Laura Maria and Terekhov, Maxim and Krause, Anna},
  journal = {arXiv preprint arXiv:2503.11703},
  year    = {2025}
}

TaylorNet: Learning PDEs from Non-Grid Data Paul Heinisch, Andrzej Dulny, Anna Krause, Andreas Hotho Proceedings of Machine Learning Research (PMLR)

2024

GrINd: Grid Interpolation Network for Scattered Observations Andrzej Dulny, Paul Heinisch, Andreas Hotho, Anna Krause Machine Learning and Knowledge Discovery in Databases (ECML-PKDD) arXiv

BibTeX

@inproceedings{dulny2024grind,
  title     = {GrINd: Grid Interpolation Network for Scattered Observations},
  author    = {Dulny, Andrzej and Heinisch, Paul and Hotho, Andreas and Krause, Anna},
  booktitle = {Machine Learning and Knowledge Discovery in Databases (ECML PKDD)},
  year      = {2024}
}

2023

Liquor-HGNN: A Heterogeneous Graph Neural Network for Leakage Detection in Water Distribution Networks Lernen. Wissen. Daten. Analysen. (LWDA)
Can Neural Networks Distinguish High-school Level Mathematical Concepts? ICDM 2023

TaylorPDENet: Learning PDEs from Non-Grid Data Paul Heinisch, Andrzej Dulny, Anna Krause, Andreas Hotho arXiv preprint arXiv

BibTeX

@article{heinisch2023taylorpdenet,
  title   = {TaylorPDENet: Learning PDEs from non-grid Data},
  author  = {Heinisch, Paul and Dulny, Andrzej and Krause, Anna and Hotho, Andreas},
  journal = {arXiv preprint arXiv:2306.14511},
  year    = {2023}
}

DynaBench: A Benchmark Dataset for Learning Dynamical Systems from Low-Resolution Data Andrzej Dulny, Andreas Hotho, Anna Krause Machine Learning and Knowledge Discovery in Databases (ECML-PKDD) arXiv Code

BibTeX

@inproceedings{dulny2023dynabench,
  title     = {DynaBench: A Benchmark Dataset for Learning Dynamical Systems from Low-Resolution Data},
  author    = {Dulny, Andrzej and Hotho, Andreas and Krause, Anna},
  booktitle = {Machine Learning and Knowledge Discovery in Databases (ECML PKDD)},
  year      = {2023}
}

2022

NeuralPDE: Modelling Dynamical Systems from Data Andrzej Dulny, Andreas Hotho, Anna Krause KI 2022: Advances in Artificial Intelligence arXiv

BibTeX

@inproceedings{dulny2022neuralpde,
  title     = {NeuralPDE: Modelling Dynamical Systems from Data},
  author    = {Dulny, Andrzej and Hotho, Andreas and Krause, Anna},
  booktitle = {KI 2022: Advances in Artificial Intelligence},
  year      = {2022}
}

2021

Do Different Deep Metric Learning Losses Lead to Similar Learned Features? Konstantin Kobs, Michael Steininger, Andrzej Dulny, Andreas Hotho IEEE/CVF International Conference on Computer Vision (ICCV) arXiv

BibTeX

@inproceedings{kobs2021different,
  title     = {Do Different Deep Metric Learning Losses Lead to Similar Learned Features?},
  author    = {Kobs, Konstantin and Steininger, Michael and Dulny, Andrzej and Hotho, Andreas},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year      = {2021}
}