# An Operational Perspective to Fairness Interventions: Where and How to Intervene

arXiv: https://arxiv.org/abs/2302.01574 · HTML: https://mlsanity.com/paper/2302.01574/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 72 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 30 of 41)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [Verified Uncertainty Calibration](https://mlsanity.com/paper/1909.10155/) (2019)
- [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification](https://mlsanity.com/paper/1805.12317/) (2018)
- [Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees](https://mlsanity.com/paper/1806.06055/) (2018)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Mitigating Bias in Calibration Error Estimation](https://mlsanity.com/paper/2012.08668/) (2020)
- [Multivariate Confidence Calibration for Object Detection](https://mlsanity.com/paper/2004.13546/) (2020)
- [Soft Calibration Objectives for Neural Networks](https://mlsanity.com/paper/2108.00106/) (2021)
- [Better Uncertainty Calibration via Proper Scores for Classification and Beyond](https://mlsanity.com/paper/2203.07835/) (2022)
- [Fairness Testing: A Comprehensive Survey and Analysis of Trends](https://mlsanity.com/paper/2207.10223/) (2022)
- ["What We Can't Measure, We Can't Understand": Challenges to Demographic Data Procurement in the Pursuit of Fairness](https://mlsanity.com/paper/2011.02282/) (2020)
- [DORO: Distributional and Outlier Robust Optimization](https://mlsanity.com/paper/2106.06142/) (2021)
- [Two-Player Games for Efficient Non-Convex Constrained Optimization](https://mlsanity.com/paper/1804.06500/) (2018)
- [A Unifying Theory of Distance from Calibration](https://mlsanity.com/paper/2211.16886/) (2022)
- [An Empirical Characterization of Fair Machine Learning For Clinical Risk Prediction](https://mlsanity.com/paper/2007.10306/) (2020)
- [Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policy](https://mlsanity.com/paper/2012.02972/) (2020)
- [Metrics of calibration for probabilistic predictions](https://mlsanity.com/paper/2205.09680/) (2022)
- [Awareness in Practice: Tensions in Access to Sensitive Attribute Data for Antidiscrimination](https://mlsanity.com/paper/1912.06171/) (2019)
- [Binary Classifier Calibration using an Ensemble of Near Isotonic Regression Models](https://mlsanity.com/paper/1511.05191/) (2015)

## Built on by (most cited first, 1 of 1)

- [Disentangling and Operationalizing AI Fairness at LinkedIn](https://mlsanity.com/paper/2306.00025/) (2023)

## Abstract (arXiv)

As AI-based decision systems proliferate, their successful operationalization requires balancing multiple desiderata: predictive performance, disparity across groups, safeguarding sensitive group attributes (e.g., race), and engineering cost. We present a holistic framework for evaluating and contextualizing fairness interventions with respect to the above desiderata. The two key points of practical consideration are where (pre-, in-, post-processing) and how (in what way the sensitive group data is used) the intervention is introduced. We demonstrate our framework with a case study on predictive parity. In it, we first propose a novel method for achieving predictive parity fairness without using group data at inference time via distibutionally robust optimization. Then, we showcase the effectiveness of these methods in a benchmarking study of close to 400 variations across two major model types (XGBoost vs. Neural Net), ten datasets, and over twenty unique methodologies. Methodological insights derived from our empirical study inform the practical design of ML workflow with fairness as a central concern. We find predictive parity is difficult to achieve without using group data, and despite requiring group data during model training (but not inference), distributionally robust methods we develop provide significant Pareto improvement. Moreover, a plain XGBoost model often Pareto-dominates neural networks with fairness interventions, highlighting the importance of model inductive bias.