Work

How divergent is your data?

Year: 2021

Type: article

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.

Source: Proceedings of the VLDB Endowment

DOI: 10.14778/3476311.3476357

Authors: Eliana Pastor, Andrew Gavgavian, Elena Baralis, Luca de Alfaro

Institutions: Politecnico di Torino, University of California, Santa Cruz

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W3197613133

FWCI: 0.968

Cites: 13

Cited by: 15

Related to: 10