A fuzzy-rough uncertainty measure to discover bias encoded explicitly or implicitly in features of structured pattern classification datasets

08/20/2021
by   Gonzalo Nápoles, et al.
0

The need to measure bias encoded in tabular data that are used to solve pattern recognition problems is widely recognized by academia, legislators and enterprises alike. In previous work, we proposed a bias quantification measure, called fuzzy-rough uncer-tainty, which relies on the fuzzy-rough set theory. The intuition dictates that protected features should not change the fuzzy-rough boundary regions of a decision class significantly. The extent to which this happens is a proxy for bias expressed as uncertainty in adecision-making context. Our measure's main advantage is that it does not depend on any machine learning prediction model but adistance function. In this paper, we extend our study by exploring the existence of bias encoded implicitly in non-protected featuresas defined by the correlation between protected and unprotected attributes. This analysis leads to four scenarios that domain experts should evaluate before deciding how to tackle bias. In addition, we conduct a sensitivity analysis to determine the fuzzy operatorsand distance function that best capture change in the boundary regions.

READ FULL TEXT
research
12/06/2022

Fuzzy Rough Sets Based on Fuzzy Quantification

One of the weaknesses of classical (fuzzy) rough sets is their sensitivi...
research
05/16/2023

Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps

In this paper, we integrate the concepts of feature importance with impl...
research
07/29/2023

Relational correspondences for L-fuzzy rough approximations defined on De Morgan Heyting algebras

Bin Pang, Ju-Sheng Mi, and Wei Yao introduced in 2019 the L-fuzzy rough ...
research
02/22/2022

Choquet-Based Fuzzy Rough Sets

Fuzzy rough set theory can be used as a tool for dealing with inconsiste...
research
11/25/2022

Evaluation of the impact of the indiscernibility relation on the fuzzy-rough nearest neighbours algorithm

Fuzzy rough sets are well-suited for working with vague, imprecise or un...
research
10/15/2014

A two-pass fuzzy-geno approach to pattern classification

The work presents an extension of the fuzzy approach to 2-D shape recogn...
research
08/01/2009

Knowledge Discovery of Hydrocyclone s Circuit Based on SONFIS and SORST

This study describes application of some approximate reasoning methods t...

Please sign up or login with your details

Forgot password? Click here to reset