Uncovering Fairness through Data Complexity as an Early Indicator
This addresses fairness concerns for practitioners in classification tasks by providing data-centric indicators to proactively guide bias mitigation.
The paper tackles the problem of fairness in machine learning by investigating how disparities in classification complexity between privileged and unprivileged groups correlate with fairness metrics, finding that quantifying these complexity differences can serve as early indicators of potential unfairness.
Fairness constitutes a concern within machine learning (ML) applications. Currently, there is no study on how disparities in classification complexity between privileged and unprivileged groups could influence the fairness of solutions, which serves as a preliminary indicator of potential unfairness. In this work, we investigate this gap, specifically, we focus on synthetic datasets designed to capture a variety of biases ranging from historical bias to measurement and representational bias to evaluate how various complexity metrics differences correlate with group fairness metrics. We then apply association rule mining to identify patterns that link disproportionate complexity differences between groups with fairness-related outcomes, offering data-centric indicators to guide bias mitigation. Our findings are also validated by their application in real-world problems, providing evidence that quantifying group-wise classification complexity can uncover early indicators of potential fairness challenges. This investigation helps practitioners to proactively address bias in classification tasks.