# Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations

arXiv: https://arxiv.org/abs/1707.00075 · HTML: https://mlsanity.com/paper/1707.00075/

## Key facts

- Cited by 165 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2017.

## Built on by (most cited first, 30 of 165)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability](https://mlsanity.com/paper/2204.08570/) (2022)
- [EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks](https://mlsanity.com/paper/2108.05233/) (2021)
- [Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics](https://mlsanity.com/paper/2106.14574/) (2021)
- [FairCLIP: Harnessing Fairness in Vision-Language Learning](https://mlsanity.com/paper/2403.19949/) (2024)
- [You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments](https://mlsanity.com/paper/2205.15967/) (2022)
- [Learning Fair Node Representations with Graph Counterfactual Fairness](https://mlsanity.com/paper/2201.03662/) (2022)
- [Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers](https://mlsanity.com/paper/2203.04913/) (2022)
- [Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning](https://mlsanity.com/paper/2108.08435/) (2021)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features](https://mlsanity.com/paper/2104.14537/) (2021)
- [Personalized Counterfactual Fairness in Recommendation](https://mlsanity.com/paper/2105.09829/) (2021)
- [Representation Bias in Data: A Survey on Identification and Resolution Techniques](https://mlsanity.com/paper/2203.11852/) (2022)
- [FMP: Toward Fair Graph Message Passing against Topology Bias](https://mlsanity.com/paper/2202.04187/) (2022)
- [Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning](https://mlsanity.com/paper/2106.02705/) (2021)
- [FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods](https://mlsanity.com/paper/2306.09468/) (2023)
- [Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization](https://mlsanity.com/paper/2306.09264/) (2023)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Fair Node Representation Learning via Adaptive Data Augmentation](https://mlsanity.com/paper/2201.08549/) (2022)
- [Fairness in Recommendation: Foundations, Methods and Applications](https://mlsanity.com/paper/2205.13619/) (2022)
- [Estimating and Improving Fairness with Adversarial Learning](https://mlsanity.com/paper/2103.04243/) (2021)
- [Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection](https://mlsanity.com/paper/2305.10204/) (2023)
- [Efficient fair PCA for fair representation learning](https://mlsanity.com/paper/2302.13319/) (2023)
- [FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis](https://mlsanity.com/paper/2310.05055/) (2023)
- [Graph Condensation: A Survey](https://mlsanity.com/paper/2401.11720/) (2024)
- [Longitudinal Fairness with Censorship](https://mlsanity.com/paper/2203.16024/) (2022)
- [FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning](https://mlsanity.com/paper/2208.10013/) (2022)
- [FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons](https://mlsanity.com/paper/2204.02567/) (2022)
- [Transferring Fairness under Distribution Shifts via Fair Consistency Regularization](https://mlsanity.com/paper/2206.12796/) (2022)

## Abstract (arXiv)

How can we learn a classifier that is "fair" for a protected or sensitive group, when we do not know if the input to the classifier belongs to the protected group? How can we train such a classifier when data on the protected group is difficult to attain? In many settings, finding out the sensitive input attribute can be prohibitively expensive even during model training, and sometimes impossible during model serving. For example, in recommender systems, if we want to predict if a user will click on a given recommendation, we often do not know many attributes of the user, e.g., race or age, and many attributes of the content are hard to determine, e.g., the language or topic. Thus, it is not feasible to use a different classifier calibrated based on knowledge of the sensitive attribute. Here, we use an adversarial training procedure to remove information about the sensitive attribute from the latent representation learned by a neural network. In particular, we study how the choice of data for the adversarial training effects the resulting fairness properties. We find two interesting results: a small amount of data is needed to train these adversarial models, and the data distribution empirically drives the adversary's notion of fairness.