Giuseppe Casalicchio

Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges

Oct 19, 2020
Christoph Molnar, Giuseppe Casalicchio, Bernd Bischl

Pitfalls to Avoid when Interpreting Machine Learning Models

Jul 08, 2020
Christoph Molnar, Gunnar König, Julia Herbinger, Timo Freiesleben, Susanne Dandl, Christian A. Scholbeck, Giuseppe Casalicchio, Moritz Grosse-Wentrup, Bernd Bischl

* This article was accepted at the ICML 2020 workshop XXAI: Extending Explainable AI Beyond Deep Models and Classifiers (see http://interpretable-ml.org/icml2020workshop/ )

Access Paper or Ask Questions

Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approach

Jun 08, 2020
Christoph Molnar, Gunnar König, Bernd Bischl, Giuseppe Casalicchio

Access Paper or Ask Questions

Sampling, Intervention, Prediction, Aggregation: A Generalized Framework for Model Agnostic Interpretations

Apr 08, 2019
Christian A. Scholbeck, Christoph Molnar, Christian Heumann, Bernd Bischl, Giuseppe Casalicchio

Access Paper or Ask Questions

Component-Wise Boosting of Targets for Multi-Output Prediction

Apr 08, 2019
Quay Au, Daniel Schalk, Giuseppe Casalicchio, Ramona Schoedel, Clemens Stachl, Bernd Bischl

Access Paper or Ask Questions

Quantifying Interpretability of Arbitrary Machine Learning Models Through Functional Decomposition

Apr 08, 2019
Christoph Molnar, Giuseppe Casalicchio, Bernd Bischl

Access Paper or Ask Questions

Visualizing the Feature Importance for Black Box Models

Jul 07, 2018
Giuseppe Casalicchio, Christoph Molnar, Bernd Bischl

* Update: Reorganized paper, improved method description, simulation added. Accepted at the Conference Track of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2018)

Access Paper or Ask Questions

OpenML Benchmarking Suites and the OpenML100

Aug 11, 2017
Bernd Bischl, Giuseppe Casalicchio, Matthias Feurer, Frank Hutter, Michel Lang, Rafael G. Mantovani, Jan N. van Rijn, Joaquin Vanschoren

* Submitted to MLOSS

Access Paper or Ask Questions

OpenML: An R Package to Connect to the Machine Learning Platform OpenML

May 04, 2017
Giuseppe Casalicchio, Jakob Bossek, Michel Lang, Dominik Kirchhoff, Pascal Kerschke, Benjamin Hofner, Heidi Seibold, Joaquin Vanschoren, Bernd Bischl

Access Paper or Ask Questions

Multilabel Classification with R Package mlr

Apr 03, 2017
Philipp Probst, Quay Au, Giuseppe Casalicchio, Clemens Stachl, Bernd Bischl

* The R Journal 9/1 (2017) 352-369
* 18 pages, 2 figures, to be published in R Journal; reference corrected

Access Paper or Ask Questions