# Average Individual Fairness: Algorithms, Generalization and Experiments

arXiv: https://arxiv.org/abs/1905.10607 · HTML: https://mlsanity.com/paper/1905.10607/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2019.

## Built on by (most cited first, 30 of 46)

- [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021)
- [Learning Fair Node Representations with Graph Counterfactual Fairness](https://mlsanity.com/paper/2201.03662/) (2022)
- [Fair and Optimal Classification via Post-Processing](https://mlsanity.com/paper/2211.01528/) (2022)
- [Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation](https://mlsanity.com/paper/2101.04108/) (2021)
- [FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods](https://mlsanity.com/paper/2306.09468/) (2023)
- [An Empirical Framework for Domain Generalization in Clinical Settings](https://mlsanity.com/paper/2103.11163/) (2021)
- [Optimising Equal Opportunity Fairness in Model Training](https://mlsanity.com/paper/2205.02393/) (2022)
- [Learning fair representation with a parametric integral probability metric](https://mlsanity.com/paper/2202.02943/) (2022)
- [Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud](https://mlsanity.com/paper/2109.03285/) (2021)
- [What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective](https://mlsanity.com/paper/2206.04101/) (2022)
- [Removing biased data to improve fairness and accuracy](https://mlsanity.com/paper/2102.03054/) (2021)
- [Unified Group Fairness on Federated Learning](https://mlsanity.com/paper/2111.04986/) (2021)
- [Omnipredictors for Constrained Optimization](https://mlsanity.com/paper/2209.07463/) (2022)
- [Individually Fair Gradient Boosting](https://mlsanity.com/paper/2103.16785/) (2021)
- [Rethinking Fair Graph Neural Networks from Re-balancing](https://mlsanity.com/paper/2407.11624/) (2024)
- [Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing](https://mlsanity.com/paper/2104.01634/) (2021)
- [Learning Antidote Data to Individual Unfairness](https://mlsanity.com/paper/2211.15897/) (2022)
- [ACROCPoLis: A Descriptive Framework for Making Sense of Fairness](https://mlsanity.com/paper/2304.11217/) (2023)
- [Monitoring Algorithmic Fairness](https://mlsanity.com/paper/2305.15979/) (2023)
- [FFPDG: Fast, Fair and Private Data Generation](https://mlsanity.com/paper/2307.00161/) (2023)
- [Monitoring Algorithmic Fairness under Partial Observations](https://mlsanity.com/paper/2308.00341/) (2023)
- [Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools](https://mlsanity.com/paper/2309.17337/) (2023)
- [Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset](https://mlsanity.com/paper/2402.17013/) (2024)
- [Metrizing Fairness](https://mlsanity.com/paper/2205.15049/) (2022)
- [Lexicographically Fair Learning: Algorithms and Generalization](https://mlsanity.com/paper/2102.08454/) (2021)
- [Fairness in Forecasting of Observations of Linear Dynamical Systems](https://mlsanity.com/paper/2209.05274/) (2022)
- [Manifestations of Xenophobia in AI Systems](https://mlsanity.com/paper/2212.07877/) (2022)
- [Rethinking Individual Fairness in Deepfake Detection](https://mlsanity.com/paper/2507.14326/) (2025)
- [Subgroup Fairness in Two-Sided Markets](https://mlsanity.com/paper/2106.02702/) (2021)
- [Systematic Evaluation of Predictive Fairness](https://mlsanity.com/paper/2210.08758/) (2022)

## Abstract (arXiv)

We propose a new family of fairness definitions for classification problems that combine some of the best properties of both statistical and individual notions of fairness. We posit not only a distribution over individuals, but also a distribution over (or collection of) classification tasks. We then ask that standard statistics (such as error or false positive/negative rates) be (approximately) equalized across individuals, where the rate is defined as an expectation over the classification tasks. Because we are no longer averaging over coarse groups (such as race or gender), this is a semantically meaningful individual-level constraint. Given a sample of individuals and classification problems, we design an oracle-efficient algorithm (i.e. one that is given access to any standard, fairness-free learning heuristic) for the fair empirical risk minimization task. We also show that given sufficiently many samples, the ERM solution generalizes in two directions: both to new individuals, and to new classification tasks, drawn from their corresponding distributions. Finally we implement our algorithm and empirically verify its effectiveness.