Comparative Separation: Evaluating Separation on Comparative Judgment Test Data

TL;DR

This paper introduces comparative separation, a new fairness evaluation method using comparative judgment test data, which reduces human labeling effort and is shown to be equivalent to traditional separation in binary classification.

Contribution

It defines the novel fairness notion of comparative separation, develops evaluation metrics, and demonstrates its theoretical and empirical equivalence to separation in binary classification.

Findings

Comparative separation is equivalent to separation in binary classification.

Using comparative judgment data reduces labeling effort.

The method provides a practical way to evaluate fairness without ground truth labels.

Abstract

This research seeks to benefit the software engineering society by proposing comparative separation, a novel group fairness notion to evaluate the fairness of machine learning software on comparative judgment test data. Fairness issues have attracted increasing attention since machine learning software is increasingly used for high-stakes and high-risk decisions. It is the responsibility of all software developers to make their software accountable by ensuring that the machine learning software do not perform differently on different sensitive groups -- satisfying the separation criterion. However, evaluation of separation requires ground truth labels for each test data point. This motivates our work on analyzing whether separation can be evaluated on comparative judgment test data. Instead of asking humans to provide the ratings or categorical labels on each test data point, comparative judgments are made between pairs of data points such as A is better than B. According to the law of comparative judgment, providing such comparative judgments yields a lower cognitive burden for humans than providing ratings or categorical labels. This work first defines the novel fairness notion comparative separation on comparative judgment test data, and the metrics to evaluate comparative separation. Then, both theoretically and empirically, we show that in binary classification problems, comparative separation is equivalent to separation. Lastly, we analyze the number of test data points and test data pairs required to achieve the same level of statistical power in the evaluation of separation and comparative separation, respectively. This work is the first to explore fairness evaluation on comparative judgment test data. It shows the feasibility and the practical benefits of using comparative judgment test data for model evaluations.