Please visit my Google Scholar profile for an up-to-date overview of my publications.
Publications
Gunnar König, Timo Freiesleben, and Moritz Grosse-Wentrup.
“Improvement-Focused Causal Recourse”
forthcoming (AAAI ‘23)
arXiv preprint arXiv:2210.15709 (2022). [pdf]
Christoph Luther*, Gunnar König* and Moritz Grosse-Wentrup
“Efficient SAGE Estimation via Causal Structure Learning”
forthcoming (AISTATS ‘23) [pdf]
Christoph Molnar, Gunnar König, et al.
“General pitfalls of model-agnostic interpretation methods for machine learning models.”
xxAI-Beyond Explainable AI: ICML Workshop, Revised and Extended Papers.
Cham: Springer International Publishing, (2022). [pdf]
Gunnar König, Christoph Molnar, Bernd Bischl, and Moritz Grosse-Wentrup
“Relative feature importance.”
2020 25th International Conference on Pattern Recognition (ICPR). IEEE, 2021. [pdf]
Christoph Molnar, et al.
“Model-agnostic Feature Importance and Effects with Dependent Features–A Conditional Subgroup Approach.”
Data Mining and Knowledge Discovery (2023): 1-39. [pdf]
Preprints
Timo Freiesleben, Gunnar König, Christoph Molnar, and Alvaro Tejero-Cantero
“Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena.”
arXiv preprint arXiv:2206.05487 (2022). [pdf]
Christoph Molnar, Timo Freiesleben, Gunnar König, et al.
“Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process.”
arXiv preprint arXiv:2109.01433 (2021). [pdf]
Gunnar König, et al.
“Decomposition of Global Feature Importance into Direct and Associative Components (DEDACT).”
arXiv preprint arXiv:2106.08086 (2021). [pdf]