Trustworthy Machine Learning

RUB
INI
Research Groups
Trustworthy Machine Learning

About Us
Publications

Machine learning has the potential for tremendous health innovations, but applying it in healthcare poses novel and interesting challenges. Data privacy is paramount, applications require high confidence in model quality, and practitioners demand explainable and comprehensible models. Ultimately, practitioners and patients alike must be able to trust these methods. In our research group on Trustworthy Machine Learning we tackle these challenges, investigating novel approaches to privacy-preserving federated learning, the theoretical foundations of deep learning, and collaborative training of explainable models.

Open Positions

Full Ph.D. Position (requires Master’s degree)
Scientific Software Developer
We offer Master and Bachelor theses

If you are interested, please send an email to Michael Kamp.

Group Leader

Dr. Michael Kamp

Members

Amr Abourayya, M.Sc.

External Homepage

2023

Federated Learning from Small Datasets
Kamp, M., Fischer, J., & Vreeken, J.
In International Conference on Learning Representations (ICLR)

federatedlearningsmalldatasets

@inproceedings{KampFischerVreeken2023, author = {Kamp, Michael and Fischer, Jonas and Vreeken, Jilles}, title = {Federated Learning from Small Datasets}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023}, }

Kamp, M., Fischer, J., & Vreeken, J. (2023). Federated Learning from Small Datasets. In International Conference on Learning Representations (ICLR).
Nothing but Regrets - Privacy-Preserving Federated Causal Discovery
Mian, O., Kaltenpoth, D., Kamp, M., & Vreeken, J.
In International Conference on Artificial Intelligence and Statistics (AISTATS)

@inproceedings{MianKaltenpothKampEtAl2023, author = {Mian, Osman and Kaltenpoth, David and Kamp, Michael and Vreeken, Jilles}, title = {Nothing but Regrets - Privacy-Preserving Federated Causal Discovery}, booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)}, year = {2023}, }

Mian, O., Kaltenpoth, D., Kamp, M., & Vreeken, J. (2023). Nothing but Regrets - Privacy-Preserving Federated Causal Discovery. In International Conference on Artificial Intelligence and Statistics (AISTATS).
Information-Theoretic Causal Discovery and Intervention Detection over Multiple Environments
Mian, O., Kamp, M., & Vreeken, J.
In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)

mian2023information

@inproceedings{MianKampVreeken2023, author = {Mian, Osman and Kamp, Michael and Vreeken, Jilles}, title = {Information-Theoretic Causal Discovery and Intervention Detection over Multiple Environments}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)}, year = {2023}, }

Mian, O., Kamp, M., & Vreeken, J. (2023). Information-Theoretic Causal Discovery and Intervention Detection over Multiple Environments. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).

2022

AIMHI: Protecting Sensitive Data through Federated Co-Training
Abourayya, A., Kamp, M., Ayday, E., Kleesiek, J., Rao, K., Webb, G. I., & Rao, B.
In FL-NeurIPS 2022)

@inproceedings{AbourayyaKampAydayEtAl2022, author = {Abourayya, Amr and Kamp, Michael and Ayday, Erman and Kleesiek, Jens and Rao, Kanishka and Webb, Geoffrey I. and Rao, Bharat}, title = {AIMHI: Protecting Sensitive Data through Federated Co-Training}, booktitle = {FL-NeurIPS 2022)}, year = {2022}, }

Abourayya, A., Kamp, M., Ayday, E., Kleesiek, J., Rao, K., Webb, G. I., & Rao, B. (2022). AIMHI: Protecting Sensitive Data through Federated Co-Training. In FL-NeurIPS 2022).

Open-Source Skull Reconstruction with MONAI

Li, J., Ferreira, A., Puladi, B., Alves, V., Kamp, M., Kim, M. -S., et al.

arXiv preprint arXiv:2211.14051

@article{LiFerreiraPuladiEtAl2022,
	author		=	{Li, Jianning and Ferreira, André and Puladi, Behrus and Alves, Victor and Kamp, Michael and Kim, Moon-Sung and Nensa, Felix and Kleesiek, Jens and Ahmadi, Seyed-Ahmad and Egger, Jan},
	title		=	{Open-Source Skull Reconstruction with MONAI},
	journal		=	{arXiv preprint arXiv:2211.14051},
	year		=	{2022},
}

Regret-based Federated Causal Discovery
Mian, O., Kaltenpoth, D., & Kamp, M.
In The KDD′22 Workshop on Causal Discovery (pp. 61–69) PMLR

@inproceedings{MianKaltenpothKamp2022, author = {Mian, Osman and Kaltenpoth, David and Kamp, Michael}, title = {Regret-based Federated Causal Discovery}, booktitle = {The KDD′22 Workshop on Causal Discovery}, pages = {61–69}, organization = {PMLR}, year = {2022}, }

Mian, O., Kaltenpoth, D., & Kamp, M.. (2022). Regret-based Federated Causal Discovery. In The KDD′22 Workshop on Causal Discovery (pp. 61–69). PMLR.
When, Where and How does it fail? A Spatial-temporal Visual Analytics Approach for Interpretable Object Detection in Autonomous Driving
Wang, J., Li, Y., Zhou, Z., Wang, C., Hou, Y., Zhang, L., et al.
IEEE Transactions on Visualization and Computer Graphics

@article{WangLiZhouEtAl2022, author = {Wang, Junhong and Li, Yun and Zhou, Zhaoyu and Wang, Chengshun and Hou, Yijie and Zhang, Li and Xue, Xiangyang and Kamp, Michael and Zhang, Xiaolong and Chen, Siming}, title = {When, Where and How does it fail? A Spatial-temporal Visual Analytics Approach for Interpretable Object Detection in Autonomous Driving}, journal = {IEEE Transactions on Visualization and Computer Graphics}, year = {2022}, }

Wang, J., Li, Y., Zhou, Z., Wang, C., Hou, Y., Zhang, L., et al. (2022). When, Where and How does it fail? A Spatial-temporal Visual Analytics Approach for Interpretable Object Detection in Autonomous Driving. IEEE Transactions on Visualization and Computer Graphics.

2021

Artificial Neural Networks Implementation to Predict the Solution of Nonlinear ODE System for the Application to Turbulent Combustion Modeling
Abourayya, A.
Master’s thesis, TU Wien

link

@mastersthesis{Abourayya2021, author = {Abourayya, Amr}, title = {Artificial Neural Networks Implementation to Predict the Solution of Nonlinear ODE System for the Application to Turbulent Combustion Modeling}, year = {2021}, doi = {10.34726/HSS.2021.95801}, }

Abourayya, A. (2021). Artificial Neural Networks Implementation to Predict the Solution of Nonlinear ODE System for the Application to Turbulent Combustion Modeling. Master’s thesis, TU Wien. Retrieved from https://repositum.tuwien.at/handle/20.500.12708/18760
FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
Li, X., Jiang, M., Zhang, X., Kamp, M., & Dou, Q.
In International Conference on Learning Representations

@inproceedings{LiJiangZhangEtAl2021, author = {Li, Xiaoxiao and Jiang, Meirui and Zhang, Xiaofei and Kamp, Michael and Dou, Qi}, title = {FedBN: Federated Learning on Non-IID Features via Local Batch Normalization}, booktitle = {International Conference on Learning Representations}, year = {2021}, }

Li, X., Jiang, M., Zhang, X., Kamp, M., & Dou, Q. (2021). FedBN: Federated Learning on Non-IID Features via Local Batch Normalization. In International Conference on Learning Representations.
Relative flatness and generalization
Petzka, H., Kamp, M., Adilova, L., Sminchisescu, C., & Boley, M.
Advances in neural information processing systems, 34, 18420–18432

@article{PetzkaKampAdilovaEtAl2021, author = {Petzka, Henning and Kamp, Michael and Adilova, Linara and Sminchisescu, Cristian and Boley, Mario}, title = {Relative flatness and generalization}, journal = {Advances in neural information processing systems}, volume = {34}, pages = {18420–18432}, year = {2021}, }

Petzka, H., Kamp, M., Adilova, L., Sminchisescu, C., & Boley, M. (2021). Relative flatness and generalization. Advances in neural information processing systems, 34, 18420–18432.

2018

Unveiling CO adsorption on Cu surfaces: new insights from molecular orbital principles
Gameel, K. M., Sharafeldin, I. M., Abourayya, A. U., Biby, A. H., & Allam, N. K.
Physical Chemistry Chemical Physics, 20(40), 25892–25900

@article{GameelSharafeldinAbourayyaEtAl2018, author = {Gameel, Kareem M. and Sharafeldin, Icell M. and Abourayya, Amr U. and Biby, Ahmed H. and Allam, Nageh K.}, title = {Unveiling CO adsorption on Cu surfaces: new insights from molecular orbital principles}, journal = {Physical Chemistry Chemical Physics}, volume = {20}, number = {40}, pages = {25892–25900}, year = {2018}, doi = {10.1039/c8cp04253e}, }

Gameel, K. M., Sharafeldin, I. M., Abourayya, A. U., Biby, A. H., & Allam, N. K. (2018). Unveiling CO adsorption on Cu surfaces: new insights from molecular orbital principles. Physical Chemistry Chemical Physics, 20(40), 25892–25900. http://doi.org/10.1039/c8cp04253e

2017

Theoretical and DFT Analysis of the CO Adsorption Mechanism Late Transition Metal Surfaces
Abourayya, A., Gameel, K. M., Sharafeldin, I. M., Biby, A. H., & Allam, N. K.
NanoWorld Conference, Bosten, USA

@article{AbourayyaGameelSharafeldinEtAl2017, author = {Abourayya, Amr and Gameel, Kareem M and Sharafeldin, Icell M and Biby, Ahmed H and Allam, Nageh K}, title = {Theoretical and DFT Analysis of the CO Adsorption Mechanism Late Transition Metal Surfaces}, journal = {NanoWorld Conference, Bosten, USA}, year = {2017}, }

Abourayya, A., Gameel, K. M., Sharafeldin, I. M., Biby, A. H., & Allam, N. K. (2017). Theoretical and DFT Analysis of the CO Adsorption Mechanism Late Transition Metal Surfaces. NanoWorld Conference, Bosten, USA.

About the INI

The Institut für Neuroinformatik (INI) is a central research unit of the Ruhr-Universität Bochum. We aim to understand the fundamental principles through which organisms generate behavior and cognition while linked to their environments through sensory systems and while acting in those environments through effector systems. Inspired by our insights into such natural cognitive systems, we seek new solutions to problems of information processing in artificial cognitive systems. We draw from a variety of disciplines that include experimental approaches from psychology and neurophysiology as well as theoretical approaches from physics, mathematics, electrical engineering and applied computer science, in particular machine learning, artificial intelligence, and computer vision.

Contact

Universitätsstr. 150, Building NB, Room 3/32
D-44801 Bochum, Germany

Tel: (+49) 234 32-28967
Fax: (+49) 234 32-14210

sekretariat@ini.rub.de
www.ini.rub.de