10.09.2021
MCML at ECML-PKDD 2021
Three Accepted Papers (2 Main, and 1 Workshop)
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Virtual, Sep 13-17, 2021
We are happy to announce that MCML researchers have contributed a total of 3 papers to ECML-PKDD 2021: 2 Main, and 1 Workshop papers. Congrats to our researchers!
Main Track (2 papers)
P. F. M. Baumann • T. Hothorn • D. Rügamer
Deep Conditional Transformation Models.
ECML-PKDD 2021 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Virtual, Sep 13-17, 2021. DOI
Deep Conditional Transformation Models.
ECML-PKDD 2021 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Virtual, Sep 13-17, 2021. DOI
J. Liu • I. Chiotellis • R. Triebel • D. Cremers
Effective Version Space Reduction for Convolutional Neural Networks.
ECML-PKDD 2021 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Virtual, Sep 13-17, 2021. DOI
Effective Version Space Reduction for Convolutional Neural Networks.
ECML-PKDD 2021 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Virtual, Sep 13-17, 2021. DOI
Workshops (1 paper)
S. Coors • D. Schalk • B. Bischl • D. Rügamer
Automatic Componentwise Boosting: An Interpretable AutoML System.
ADS @ECML-PKDD 2021 - Automating Data Science Workshop at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Virtual, Sep 13-17, 2021. arXiv
Automatic Componentwise Boosting: An Interpretable AutoML System.
ADS @ECML-PKDD 2021 - Automating Data Science Workshop at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Virtual, Sep 13-17, 2021. arXiv
Related
26.08.2026
Transparency for Global Health Aid
MCML PI Stefan Feuerriegel and his team use machine learning to uncover disparities in the global allocation of health aid.
25.08.2026
David Rügamer: We Need Uncertainty Quantification
MCML PI David Rügamer explains why uncertainty quantification is essential for building trustworthy AI and making informed decisions.
