Tracking and Improving Information in the Service of Fairness
| Autor: | Michael P. Kim, Sumegha Garg, Omer Reingold |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Service (systems architecture) business.industry Computer science 05 social sciences Machine Learning (stat.ML) 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Machine Learning (cs.LG) Range (mathematics) Statistics - Machine Learning 0502 economics and business Fairness measure Artificial intelligence Tracking (education) 050207 economics business computer Selection (genetic algorithm) 0105 earth and related environmental sciences Simple (philosophy) |
| Zdroj: | EC |
| Popis: | As algorithmic prediction systems have become widespread, fears that these systems may inadvertently discriminate against members of underrepresented populations have grown. With the goal of understanding fundamental principles that underpin the growing number of approaches to mitigating algorithmic discrimination, we investigate the role of information in fair prediction. A common strategy for decision-making uses a predictor to assign individuals a risk score; then, individuals are selected or rejected on the basis of this score. In this work, we study a formal framework for measuring the information content of predictors. Central to this framework is the notion of a refinement, first studied by Degroot and Fienberg. Intuitively, a refinement of a predictor $z$ increases the overall informativeness of the predictions without losing the information already contained in $z$. We show that increasing information content through refinements improves the downstream selection rules across a wide range of fairness measures (e.g. true positive rates, false positive rates, selection rates). In turn, refinements provide a simple but effective tool for reducing disparity in treatment and impact without sacrificing the utility of the predictions. Our results suggest that in many applications, the perceived "cost of fairness" results from an information disparity across populations, and thus, may be avoided with improved information. Appeared at EC 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|