25.11.2025

InterACT Workshop 2025

Methodological Challenges in Explainable AI

The InterACT Workshop 2025 took place at LMU Munich in September. Participants engaged in an intensive scientific exchange on methodological challenges in Explainable AI (xAI). The workshop brought together 24 researchers from eight institutions across Europe: LMU Munich, University of Bremen, University of Warsaw, University of Zurich, Norwegian Computing Center, University of Tübingen, Universidad Rey Juan Carlos Madrid, and Universidad Internacional Menéndez Pelayo Madrid. The workshop focused on Interpretable and Explainable Machine Learning (IML/xAI) and was organized by Fiona K. Ewald (LMU & MCML) with support from MCML Director Bernd Bischl.

Across poster presentations, structured brainstorming, and two idea-building sessions, participants engaged in a scientific exchange on methodological challenges in xAI. Topics included computational efficiency, feature interactions, neural network explainability, uncertainty aspects, reproducibility, structured explanation summaries, practical applications of xAI, and explainability within European governance frameworks. Several clusters identified promising follow-up directions, and one group has already produced an outcome: A tiny paper titled “Technical Considerations for XAI in AI Governance”, accepted for presentation at the EurIPS 2025 Workshop on Private AI Governance (PAIG). Multiple groups expressed interest in continuing their discussions and exploring joint work following the workshop.

The event strengthened collaboration between LMU/MCML and partner institutions, supporting MCML’s objectives in trustworthy and interpretable AI.

Planning for the next workshops is already underway: InterACT 2026 will take place at the University of Bremen from September 14 - 18, and Universidad Rey Juan Carlos Madrid has expressed interest in hosting InterACT 2027.