---
res:
  bibo_abstract:
  - Explainable Artificial Intelligence (XAI) has mainly focused on static learning
    tasks so far. In this paper, we consider XAI in the context of online learning
    in dynamic environments, such as learning from real-time data streams, where models
    are learned incrementally and continuously adapted over the course of time. More
    specifically, we motivate the problem of explaining model change, i.e. explaining
    the difference between models before and after adaptation, instead of the models
    themselves. In this regard, we provide the first efficient model-agnostic approach
    to dynamically detecting, quantifying, and explaining significant model changes.
    Our approach is based on an adaptation of the well-known Permutation Feature Importance
    (PFI) measure. It includes two hyperparameters that control the sensitivity and
    directly influence explanation frequency, so that a human user can adjust the
    method to individual requirements and application needs. We assess and validate
    our method’s efficacy on illustrative synthetic data streams with three popular
    model classes.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Maximilian
      foaf_name: Muschalik, Maximilian
      foaf_surname: Muschalik
  - foaf_Person:
      foaf_givenName: Fabian
      foaf_name: Fumagalli, Fabian
      foaf_surname: Fumagalli
      foaf_workInfoHomepage: http://www.librecat.org/personId=93420
  - foaf_Person:
      foaf_givenName: Barbara
      foaf_name: Hammer, Barbara
      foaf_surname: Hammer
  - foaf_Person:
      foaf_givenName: Eyke
      foaf_name: Huellermeier, Eyke
      foaf_surname: Huellermeier
      foaf_workInfoHomepage: http://www.librecat.org/personId=48129
  bibo_doi: 10.1007/s13218-022-00766-6
  bibo_issue: 3-4
  bibo_volume: 36
  dct_date: 2022^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/0933-1875
  - http://id.crossref.org/issn/1610-1987
  dct_language: eng
  dct_publisher: Springer Science and Business Media LLC@
  dct_subject:
  - Artificial Intelligence
  dct_title: Agnostic Explanation of Model Change based on Feature Importance@
...