21.07.2026
Timo Heiß Receives Best Student Paper Award at XAI 2026
Improving Feature Effect Estimation in Explainable AI
MCML Junior Member Timo Heiß received the Best Student Paper Award at the 4th World Conference on eXplainable Artificial Intelligence (XAI 2026) for the paper Analyzing Error Sources in Global Feature Effect Estimation. Co-authored with Coco Bögel, Bernd Bischl, and Giuseppe Casalicchio, the work was recognized for its outstanding contribution to explainable AI.
The paper provides a systematic analysis of the different sources of error in global feature effect estimation, a key technique for interpreting machine learning models. By decomposing these errors, the researchers address the practical question of whether feature effects should be estimated on training or holdout data, offering guidance that helps make explainable AI methods more reliable and robust.
Related
31.07.2026
Benedikt Wiestler: We Want to Build a Time Machine
MCML PI Benedikt Wiestler explains how AI models help to develop specific strategies in clinical therapy for brain tumor patients.
28.07.2026
Gaps in the Benchmark: Why Medical AI Fails in the Real World
MCML researchers show in Nature Health how dynamic red teaming exposes hidden weaknesses in Medical AI beyond static benchmarks.
