Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916152698994688 |
|---|---|
| author | Cooper, A. Feder Lee, Katherine Choksi, Madiha Zahrah Barocas, Solon De Sa, Christopher Grimmelmann, James Kleinberg, Jon Sen, Siddhartha Zhang, Baobao |
| author_facet | Cooper, A. Feder Lee, Katherine Choksi, Madiha Zahrah Barocas, Solon De Sa, Christopher Grimmelmann, James Kleinberg, Jon Sen, Siddhartha Zhang, Baobao |
| contents | Variance in predictions across different trained models is a significant, under-explored source of error in fair binary classification. In practice, the variance on some data examples is so large that decisions can be effectively arbitrary. To investigate this problem, we take an experimental approach and make four overarching contributions: We: 1) Define a metric called self-consistency, derived from variance, which we use as a proxy for measuring and reducing arbitrariness; 2) Develop an ensembling algorithm that abstains from classification when a prediction would be arbitrary; 3) Conduct the largest to-date empirical study of the role of variance (vis-a-vis self-consistency and arbitrariness) in fair binary classification; and, 4) Release a toolkit that makes the US Home Mortgage Disclosure Act (HMDA) datasets easily usable for future research. Altogether, our experiments reveal shocking insights about the reliability of conclusions on benchmark datasets. Most fair binary classification benchmarks are close-to-fair when taking into account the amount of arbitrariness present in predictions -- before we even try to apply any fairness interventions. This finding calls into question the practical utility of common algorithmic fairness methods, and in turn suggests that we should reconsider how we choose to measure fairness in binary classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_11562 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification Cooper, A. Feder Lee, Katherine Choksi, Madiha Zahrah Barocas, Solon De Sa, Christopher Grimmelmann, James Kleinberg, Jon Sen, Siddhartha Zhang, Baobao Machine Learning Artificial Intelligence Computers and Society Variance in predictions across different trained models is a significant, under-explored source of error in fair binary classification. In practice, the variance on some data examples is so large that decisions can be effectively arbitrary. To investigate this problem, we take an experimental approach and make four overarching contributions: We: 1) Define a metric called self-consistency, derived from variance, which we use as a proxy for measuring and reducing arbitrariness; 2) Develop an ensembling algorithm that abstains from classification when a prediction would be arbitrary; 3) Conduct the largest to-date empirical study of the role of variance (vis-a-vis self-consistency and arbitrariness) in fair binary classification; and, 4) Release a toolkit that makes the US Home Mortgage Disclosure Act (HMDA) datasets easily usable for future research. Altogether, our experiments reveal shocking insights about the reliability of conclusions on benchmark datasets. Most fair binary classification benchmarks are close-to-fair when taking into account the amount of arbitrariness present in predictions -- before we even try to apply any fairness interventions. This finding calls into question the practical utility of common algorithmic fairness methods, and in turn suggests that we should reconsider how we choose to measure fairness in binary classification. |
| title | Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification |
| topic | Machine Learning Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2301.11562 |