Logo Logo
Switch Language to German

Muschalik, Maximilian ORCID logoORCID: https://orcid.org/0000-0002-6921-0204; Fumagalli, Fabian ORCID logoORCID: https://orcid.org/0000-0003-3955-3510; Hammer, Barbara ORCID logoORCID: https://orcid.org/0000-0002-0935-5591 and Hüllermeier, Eyke ORCID logoORCID: https://orcid.org/0000-0002-9944-4108 (18. September 2023): iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams. Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Torino, Italy, 18-22 September, 2023. In: Machine Learning and Knowledge Discovery in Databases: Research Track, Vol. 14171 Cham: Springer. pp. 428-445

Full text not available from 'Open Access LMU'.


Existing methods for explainable artificial intelligence (XAI), including popular feature importance measures such as SAGE, are mostly restricted to the batch learning scenario. However, machine learning is often applied in dynamic environments, where data arrives continuously and learning must be done in an online manner. Therefore, we propose iSAGE, a time- and memory-efficient incrementalization of SAGE, which is able to react to changes in the model as well as to drift in the data-generating process. We further provide efficient feature removal methods that break (interventional) and retain (observational) feature dependencies. Moreover, we formally analyze our explanation method to show that iSAGE adheres to similar theoretical properties as SAGE. Finally, we evaluate our approach in a thorough experimental analysis based on well-established data sets and data streams with concept drift.

Actions (login required)

View Item View Item