InterACT

Workshop on Interpretable Machine Learning

InterACT is a collaborative workshop between the interpretable machine learning / explainable AI group led by Dr. Giuseppe Casalicchio of the Chair of Statistical Learning and Data Science (SLDS) of LMU Munich led by Prof. Dr. Bernd Bischl and the Emmy Noether Junior Research Group led by Prof. Dr. Marvin N. Wright of the Leibniz Institute for Prevention Research and Epidemiology — BIPS.

The workshop is aimed primarily at PhD students in the field of interpretable machine learning (IML) and explainable AI (XAI) and includes postdoctoral and senior researchers. It takes place annually over four days, alternating between Munich and Bremen.

Workshops

InterACT #4

Bremen, September 14 – 17, 2026

InterACT #3

Munich, September 1 – 4, 2025

InterACT #2

Bremen, September 23 – 26, 2024

Directly supported by the Minds, Media, Machines Integrated Graduate School (MMMIGS) PhD Grant Bremen. Among others, it led to Kapar et al. (2026), combining generative modeling with interpretable machine learning.

A group photo of the InterACT #2 members in front of the BIPS building

InterACT #1

Munich, November 13 – 16, 2023

Among many brainstorming sessions, it laid the foundation for Ewald et al. (2024) and spawned the “CountARFactuals” project (Dandl et al. 2024), bridging counterfactual explanations and tree-based generative modeling.

Supporting Organizations

InterACT is made possible by the following organizations whose support is greatly appreciated:

Publications

Baniecki, Hubert, Giuseppe Casalicchio, Bernd Bischl, and Przemyslaw Biecek. 2024. “On the Robustness of Global Feature Effect Explanations.” In Machine Learning and Knowledge Discovery in Databases. Research Track, edited by Albert Bifet, Jesse Davis, Tomas Krilavičius, Meelis Kull, Eirini Ntoutsi, and Indrė Žliobaitė. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-70344-7_8.

Dandl, Susanne, Kristin Blesch, Timo Freiesleben, et al. 2024. “CountARFactuals – Generating Plausible Model-Agnostic Counterfactual Explanations with Adversarial Random Forests.” In Explainable Artificial Intelligence, edited by Luca Longo, Sebastian Lapuschkin, and Christin Seifert, vol. 2155. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-63800-8_5.

Dandl, Susanne, Fiona Katharina Ewald, Enrique Valero-Leal, Bernd Bischl, and Kristin Blesch. 2025. “Technical Considerations for XAI in AI Governance.” EurIPS 2025 Workshop on Private AI Governance. https://openreview.net/forum?id=6DMzcPNOTf.

Ewald, Fiona Katharina, Ludwig Bothmann, Marvin N. Wright, Bernd Bischl, Giuseppe Casalicchio, and Gunnar König. 2024. “A Guide to Feature Importance Methods for Scientific Inference.” In Explainable Artificial Intelligence, edited by Luca Longo, Sebastian Lapuschkin, and Christin Seifert. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-63797-1_22.

Kapar, Jan, Niklas Koenen, and Martin Jullum. 2026. “What’s Wrong with Your Synthetic Tabular Data? Using Explainable AI to Evaluate Generative Models.” In Explainable Artificial Intelligence, edited by Riccardo Guidotti, Ute Schmid, and Luca Longo, vol. 2578. Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-08327-2_2.

Langbein, Sophie Hanna, Hubert Baniecki, Fabian Fumagalli, Niklas Koenen, Marvin N. Wright, and Julia Herbinger. 2026. “Functional Decomposition and Shapley Interactions for Interpreting Survival Models.” Forty-Third International Conference on Machine Learning. https://openreview.net/forum?id=SldP4LGjdz.