Identifying Reasons for Bias: An Argumentation-Based Approach
This addresses the need for transparent bias identification in algorithmic systems, particularly for stakeholders affected by unfair classifications, though it is incremental as it builds on existing argumentation frameworks.
The paper tackles the problem of identifying why individuals are classified unfairly by algorithmic decision-making systems, proposing a model-agnostic argumentation-based method that identifies attribute-value pairs contributing most to different classifications, and demonstrates its effectiveness on two fairness datasets.
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.