Jann Goschenhofer

Jann has graduated from the SLDS chair. You can find further information on his website: https://janngoschenhofer.com

About

I am a final-year PhD student at the working group for Statistical Learning and Data Science at LMU Munich in cooperation with the Fraunhofer ADA Lovelace Center where I am involved in application research across different domains. I am researching on methods for Learning with Limited Labeled Data (L3D) including but not limited to Semi-supervised-/ Self-supervised- /Weakly-supervised Learning, currently focusing on Constrained Clustering and Positive Unlabeled Learning. I am generally interested in all things low supervision including weak/ noisy/ inconsistent data annotations, model-based labeling error detection and the smart design of data annotation pipelines.

I hold a Master's Degree in Statistics from LMU and a Bachelor's Degree in Economics from Heidelberg University. Find more information about me on my personal website.

Contact

Institut für Statistik

Ludwig-Maximilians-Universität München

Ludwigstraße 33

D-80539 München

Room 139

Phone: +49 911 58061 9595

jann.goschenhofer [at] stat.uni-muenchen.de

Research Interests

You Can Find me on

References

  1. Goschenhofer J, Bischl B, Kira Z (2023) ConstraintMatch for semi-constrained Clustering. International Joint Conference on Neural Networks (IJCNN).
  2. Sieberts SK, Borzymowski H, Guan Y, Huang Y, Matzner A, Page A, Bar-Gad I, Beaulieu-Jones B, El-Hanani Y, Goschenhofer J, others (2023) Developing better digital health measures of parkinson’s disease using free living data and a crowdsourced data analysis challenge. PLOS Digital Health.
    link|pdf
    .
  3. Rodemann J, Goschenhofer J, Dorigatti E, Nagler T, Augustin T (2023) Approximately Bayes-Optimal Pseudo-Label Selection. Uncertainty in Artificial Intelligence (UAI), PMLR.
    link|pdf
    .
  4. Aßenmacher M, Rauch L, Goschenhofer J, Stephan A, Bischl B, Roth B, Sick B (2023) Towards Enhancing Deep Active Learning with WeakSupervision and Constrained Clustering. Proceedings of the Workshop on Interactive Adaptive Learning, ECML-PKDD.
    link|pdf
    .
  5. Goschenhofer J, Ragupathy P, Heumann C, Bischl B, Aßenmacher M (2022) CC-Top: Constrained Clustering for Dynamic Topic Discovery. Workshop on Ever Evolving NLP (EvoNLP).
    link|pdf
    .
  6. Dexl J, Benz M, Kuritcyn P, Wittenberg T, Bruns V, Geppert C, Hartmann A, Bischl B, Goschenhofer J (2022) Robust Colon Tissue Cartography with Semi-Supervision. Current Directions in Biomedical Engineering 8, 344–347.
    link|pdf
    .
  7. Rueger S, Goschenhofer J, Nath A, Firsching M, Ennen A, Bischl B (2022) Deep-Learning-based Aluminum Sorting on Dual Energy X-Ray Transmission Data. Sensor-based Sorting and Control.
    link|pdf
    .
  8. Kaminwar SR, Goschenhofer J, Thomas J, Thon I, Bischl B (2021) Structured Verification of Machine Learning Models in Industrial Settings. Big Data.
    link|pdf
    .
  9. Goschenhofer J, Hvingelby R, Rügamer D, Thomas J, Wagner M, Bischl B (2021) Deep Semi-Supervised Learning for Time Series Classification 20th IEEE International Conference on Machine Learning and Applications (ICMLA),
    link|pdf
    .
  10. Dorigatti E, Goschenhofer J, Schubert B, Rezaei M, Bischl B (2021) Positive-Unlabeled Learning with Uncertainty-aware Pseudo-label Selection. arXiv preprint arXiv:2109.05232.
    link|pdf
    .
  11. Pfister FMJ, Um TT, Pichler DC, Goschenhofer J, Abedinpour K, Lang M, Endo S, Ceballos-Baumann AO, Hirche S, Bischl B, others (2020) High-Resolution Motor State Detection in Parkinson’s Disease Using convolutional neural networks. Scientific reports 10, 1–11.
    link
    .
  12. Goschenhofer J, Pfister FMJ, Yuksel KA, Bischl B, Fietzek U, Thomas J (2019) Wearable-based Parkinson’s Disease Severity Monitoring using Deep Learning. Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 400–415.
    link
    .