We present DivExplorer, a tool that enables users to explore datasets and find subgroups of data for which a classifier behaves in an anomalous manner. These subgroups, denoted as divergent subgroups, may exhibit, for example, higher-than-normal false positive or negative rates. DivExplorer can be used to analyze and debug classifiers. If the data has ethical or social implications, DivExplorer can be also used to identify bias in classifiers.

How Divergent Is Your Data? / Pastor, Eliana; Gavgavian, Andrew; Baralis, Elena; de Alfaro, Luca. - ELETTRONICO. - 14:(2021), pp. 2835-2838. ((Intervento presentato al convegno 47th International Conference on Very Large Data Bases.

How Divergent Is Your Data?

Pastor, Eliana;Baralis, Elena;
2021

Abstract

We present DivExplorer, a tool that enables users to explore datasets and find subgroups of data for which a classifier behaves in an anomalous manner. These subgroups, denoted as divergent subgroups, may exhibit, for example, higher-than-normal false positive or negative rates. DivExplorer can be used to analyze and debug classifiers. If the data has ethical or social implications, DivExplorer can be also used to identify bias in classifiers.
File in questo prodotto:
File Dimensione Formato  
p2835-pastor.pdf

accesso aperto

Descrizione: Articolo principale (post-print referato)
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 572.71 kB
Formato Adobe PDF
572.71 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11583/2923192