Interpretable machine learning: Explaining change (C03)

• Subject Area: Data Management, Data-Intensive Systems, Computer Science Methods in Business Informatics
• Term: since 2021
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 438445824

Project C03 centers on how to account for dynamic properties of an explanandum. Its target is to deliver a model that will explain a drift of data that a machine learning model undergoes over time as a result of nonstationary distributions and evolving training data. The project will go beyond a mere transfer of established methodology for interpretable ML and develop a new methodology for explainable ML in the extremely relevant area of online learning. Questions to be addressed are: How to keep the frequency of model change at a reasonably low level while guaranteeing a sufficient quality and accuracy, and how to justify a model change and explain it to the user.

• DFG Programme: CRC/Transregios
• Subproject of: TRR 318: Constructing explainability
• Applicant Institution: Universität Paderborn
• Project Heads: Professorin Dr. Barbara Hammer; Professor Dr. Eyke Hüllermeier