Interpretation drift in explainable AI under label noise
Abstract The comprehensibility and human interpretation of classification models are crucial in many applications, such as decision support systems and knowledge discovery, where explanations drive action. However, the presence of class label noise, widespread in real-life data, can significantly im...
Bewaard in:
| Hoofdauteurs: | , , |
|---|---|
| Formaat: | Artigo |
| Taal: | Inglês |
| Gepubliceerd in: |
Nature Portfolio
2026-03-01
|
| Reeks: | Scientific Reports |
| Onderwerpen: | |
| Online toegang: | https://doi.org/10.1038/s41598-026-37070-4 |
| Tags: |
Geen labels, Wees de eerste die dit record labelt!
|