Christoph Molnar

According to our database, Christoph Molnar authored at least 17 papers between 2018 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process.

Christoph Molnar, Timo Freiesleben, Gunnar König, Julia Herbinger, Tim Reisinger, Giuseppe Casalicchio, Marvin N. Wright, Bernd Bischl

Proceedings of the Explainable Artificial Intelligence, 2023

2022

Model-agnostic interpretable machine learning.

Christoph Molnar

PhD thesis, 2022

Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena.

Timo Freiesleben, Gunnar König, Christoph Molnar, Álvaro Tejero-Cantero

CoRR, 2022

Marginal Effects for Non-Linear Prediction Functions.

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

CoRR, 2022

2021

Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process.

Christoph Molnar, Timo Freiesleben, Gunnar König, Giuseppe Casalicchio, Marvin N. Wright, Bernd Bischl

CoRR, 2021

2020

Pitfalls to Avoid when Interpreting Machine Learning Models.

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

CoRR, 2020

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

Christoph Molnar, Gunnar König, Bernd Bischl, Giuseppe Casalicchio

CoRR, 2020

Multi-Objective Counterfactual Explanations.

Susanne Dandl, Christoph Molnar, Martin Binder, Bernd Bischl

Proceedings of the Parallel Problem Solving from Nature - PPSN XVI, 2020

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

Christoph Molnar, Giuseppe Casalicchio, Bernd Bischl

Proceedings of the ECML PKDD 2020 Workshops, 2020

Relative Feature Importance.

Gunnar König, Christoph Molnar, Bernd Bischl, Moritz Grosse-Wentrup

Proceedings of the 25th International Conference on Pattern Recognition, 2020

General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models.

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

Proceedings of the xxAI - Beyond Explainable AI, 2020

Explainable AI Methods - A Brief Overview.

Andreas Holzinger, Anna Saranti, Christoph Molnar, Przemyslaw Biecek, Wojciech Samek

Proceedings of the xxAI - Beyond Explainable AI, 2020

2019

Quantifying Interpretability of Arbitrary Machine Learning Models Through Functional Decomposition.

Christoph Molnar, Giuseppe Casalicchio, Bernd Bischl

CoRR, 2019

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

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

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2019

Quantifying Model Complexity via Functional Decomposition for Better Post-hoc Interpretability.

Christoph Molnar, Giuseppe Casalicchio, Bernd Bischl

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2019

2018

iml: An R package for Interpretable Machine Learning.

Christoph Molnar, Giuseppe Casalicchio, Bernd Bischl

J. Open Source Softw., 2018

Visualizing the Feature Importance for Black Box Models.

Giuseppe Casalicchio, Christoph Molnar, Bernd Bischl

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2018