# iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making

arXiv: https://arxiv.org/abs/1806.01059 · HTML: https://mlsanity.com/paper/1806.01059/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2018.

## Built on by (most cited first, 30 of 64)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks](https://mlsanity.com/paper/2108.05233/) (2021)
- [Post-processing for Individual Fairness](https://mlsanity.com/paper/2110.13796/) (2021)
- [Unveiling Security, Privacy, and Ethical Concerns of ChatGPT](https://mlsanity.com/paper/2307.14192/) (2023)
- [Representation Bias in Data: A Survey on Identification and Resolution Techniques](https://mlsanity.com/paper/2203.11852/) (2022)
- [Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization](https://mlsanity.com/paper/2108.05449/) (2021)
- [Fairness in Recommendation: Foundations, Methods and Applications](https://mlsanity.com/paper/2205.13619/) (2022)
- [Ensuring User-side Fairness in Dynamic Recommender Systems](https://mlsanity.com/paper/2308.15651/) (2023)
- [Bayes-Optimal Classifiers under Group Fairness](https://mlsanity.com/paper/2202.09724/) (2022)
- [FARE: Provably Fair Representation Learning with Practical Certificates](https://mlsanity.com/paper/2210.07213/) (2022)
- [A Survey on Fairness for Machine Learning on Graphs](https://mlsanity.com/paper/2205.05396/) (2022)
- [Fairness-Aware Online Meta-learning](https://mlsanity.com/paper/2108.09435/) (2021)
- [Latent Space Smoothing for Individually Fair Representations](https://mlsanity.com/paper/2111.13650/) (2021)
- [Interpreting Unfairness in Graph Neural Networks via Training Node Attribution](https://mlsanity.com/paper/2211.14383/) (2022)
- [Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers](https://mlsanity.com/paper/2404.03192/) (2024)
- [Fair Bayes-Optimal Classifiers Under Predictive Parity](https://mlsanity.com/paper/2205.07182/) (2022)
- [Accurate Fairness: Improving Individual Fairness without Trading Accuracy](https://mlsanity.com/paper/2205.08704/) (2022)
- [Fair Enough: Searching for Sufficient Measures of Fairness](https://mlsanity.com/paper/2110.13029/) (2021)
- [Survey on Fair Reinforcement Learning: Theory and Practice](https://mlsanity.com/paper/2205.10032/) (2022)
- [Domain Adaptation meets Individual Fairness. And they get along](https://mlsanity.com/paper/2205.00504/) (2022)
- [Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning](https://mlsanity.com/paper/2208.01182/) (2022)
- [Transitioning from Real to Synthetic data: Quantifying the bias in model](https://mlsanity.com/paper/2105.04144/) (2021)
- [Fair Generalized Linear Models with a Convex Penalty](https://mlsanity.com/paper/2206.09076/) (2022)
- [Individual Fairness under Uncertainty](https://mlsanity.com/paper/2302.08015/) (2023)
- [fairmodels: A Flexible Tool For Bias Detection, Visualization, And Mitigation](https://mlsanity.com/paper/2104.00507/) (2021)
- [Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity](https://mlsanity.com/paper/2211.02139/) (2022)
- [Learning Antidote Data to Individual Unfairness](https://mlsanity.com/paper/2211.15897/) (2022)
- [Monitoring Algorithmic Fairness](https://mlsanity.com/paper/2305.15979/) (2023)
- [What will it take to generate fairness-preserving explanations?](https://mlsanity.com/paper/2106.13346/) (2021)
- [Monitoring Algorithmic Fairness under Partial Observations](https://mlsanity.com/paper/2308.00341/) (2023)

## Abstract (arXiv)

People are rated and ranked, towards algorithmic decision making in an increasing number of applications, typically based on machine learning. Research on how to incorporate fairness into such tasks has prevalently pursued the paradigm of group fairness: giving adequate success rates to specifically protected groups. In contrast, the alternative paradigm of individual fairness has received relatively little attention, and this paper advances this less explored direction. The paper introduces a method for probabilistically mapping user records into a low-rank representation that reconciles individual fairness and the utility of classifiers and rankings in downstream applications. Our notion of individual fairness requires that users who are similar in all task-relevant attributes such as job qualification, and disregarding all potentially discriminating attributes such as gender, should have similar outcomes. We demonstrate the versatility of our method by applying it to classification and learning-to-rank tasks on a variety of real-world datasets. Our experiments show substantial improvements over the best prior work for this setting.