Identifying Reasons for Bias: An Argumentation-Based Approach

TL;DR

This paper introduces a novel, model-agnostic argumentation-based approach to identify reasons for bias in individual classifications, enhancing transparency without requiring access to training data.

Contribution

It presents a new argumentation framework that explains individual classification differences, addressing transparency and data access limitations in fairness analysis.

Findings

Effective bias identification demonstrated on two datasets

Framework highlights key attribute-value pairs influencing classification

Method enhances interpretability of fairness in decision-making systems

Abstract

As algorithmic decision-making systems become more prevalent in society, ensuring the fairness of these systems is becoming increasingly important. Whilst there has been substantial research in building fair algorithmic decision-making systems, the majority of these methods require access to the training data, including personal characteristics, and are not transparent regarding which individuals are classified unfairly. In this paper, we propose a novel model-agnostic argumentation-based method to determine why an individual is classified differently in comparison to similar individuals. Our method uses a quantitative argumentation framework to represent attribute-value pairs of an individual and of those similar to them, and uses a well-known semantics to identify the attribute-value pairs in the individual contributing most to their different classification. We evaluate our method on two datasets commonly used in the fairness literature and illustrate its effectiveness in the identification of bias.