.png){kind=icon}
Return
Explaining data changes with prototypes: A measure-driven approach
.png){kind=icon}
OA
AI
DOI：10.1016/j.inffus.2025.103602.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• New measures for evaluating prototype explanations in static and dynamic settings. • RACE-P: a prototype-based algorithm for interpretable concept drift detection. • On evolving data, RACE-P showed competitive performance to drift detectors. • Prototype explanations are used to analyse concept drift, enhancing model interpretability.
Keywords:
Explainable Artificial Intelligence
Prototype explanation
Data shift
Evolving data stream
Journal
IF:
15.5
Papers:
4.2K
Citations:
2.7W
Organization
No organization information available
Cited Papers
ShareSaveShareSaveShareSaveShareSaveInterpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking.png)
Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
OAAI
Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningIF0
OAAIShareSave
View more