# Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks

arXiv: https://arxiv.org/abs/2109.00545 · HTML: https://mlsanity.com/paper/2109.00545/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 73 references that are in the map.
- First posted on arXiv 1 Sep 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Learning Gender-Neutral Word Embeddings](https://mlsanity.com/paper/1809.01496/) (2018)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [Inherent Tradeoffs in Learning Fair Representations](https://mlsanity.com/paper/1906.08386/) (2019)
- [Controllable Invariance through Adversarial Feature Learning](https://mlsanity.com/paper/1705.11122/) (2017)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [Fair Generative Modeling via Weak Supervision](https://mlsanity.com/paper/1910.12008/) (2019)
- [Invariant Representations without Adversarial Training](https://mlsanity.com/paper/1805.09458/) (2018)
- [On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset](https://mlsanity.com/paper/1906.03292/) (2019)
- [Learning Controllable Fair Representations](https://mlsanity.com/paper/1812.04218/) (2018)
- [Conditional Learning of Fair Representations](https://mlsanity.com/paper/1910.07162/) (2019)
- [Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems](https://mlsanity.com/paper/2002.00057/) (2020)
- [Provably Fair Representations](https://mlsanity.com/paper/1710.04394/) (2017)
- [Semi-Adversarial Networks: Convolutional Autoencoders for Imparting Privacy to Face Images](https://mlsanity.com/paper/1712.00321/) (2017)
- [FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test](https://mlsanity.com/paper/1405.2664/) (2014)
- [Null-sampling for Interpretable and Fair Representations](https://mlsanity.com/paper/2008.05248/) (2020)

## Built on by (most cited first, 16 of 16)

- [FARE: Provably Fair Representation Learning with Practical Certificates](https://mlsanity.com/paper/2210.07213/) (2022)
- [Model-Agnostic Gender Debiased Image Captioning](https://mlsanity.com/paper/2304.03693/) (2023)
- [Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics](https://mlsanity.com/paper/2505.06435/) (2025)
- [Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities](https://mlsanity.com/paper/2306.12609/) (2023)
- [From Global to Local: Social Bias Transfer in CLIP](https://mlsanity.com/paper/2508.17750/) (2025)
- [Learning Fair Representations with High-Confidence Guarantees](https://mlsanity.com/paper/2310.15358/) (2023)
- [AI-based association analysis for medical imaging using latent-space geometric confounder correction](https://mlsanity.com/paper/2311.12836/) (2023)
- [Long-Term Fairness in Sequential Multi-Agent Selection with Positive Reinforcement](https://mlsanity.com/paper/2407.07350/) (2024)
- [PFAttack: Stealthy Attack Bypassing Group Fairness in Federated Learning](https://mlsanity.com/paper/2410.06509/) (2024)
- [Elucidate Gender Fairness in Singing Voice Transcription](https://mlsanity.com/paper/2308.02898/) (2023)
- [Anti-Matthew FL: Bridging the Performance Gap in Federated Learning to Counteract the Matthew Effect](https://mlsanity.com/paper/2309.16338/) (2023)
- [Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning](https://mlsanity.com/paper/2508.15084/) (2025)
- [Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference](https://mlsanity.com/paper/2510.21017/) (2025)
- [Incorporating Fairness in Neighborhood Graphs for Fair Spectral Clustering](https://mlsanity.com/paper/2512.09810/) (2025)
- [FairGFL: Privacy-Preserving Fairness-Aware Federated Learning with Overlapping Subgraphs](https://mlsanity.com/paper/2512.23235/) (2025)
- [Fairness May Backfire: When Leveling-Down Occurs in Fair Machine Learning](https://mlsanity.com/paper/2603.06901/) (2026)

## Abstract (arXiv)

Motivated by scenarios where data is used for diverse prediction tasks, we study whether fair representation can be used to guarantee fairness for unknown tasks and for multiple fairness notions simultaneously. We consider seven group fairness notions that cover the concepts of independence, separation, and calibration. Against the backdrop of the fairness impossibility results, we explore approximate fairness. We prove that, although fair representation might not guarantee fairness for all prediction tasks, it does guarantee fairness for an important subset of tasks -- the tasks for which the representation is discriminative. Specifically, all seven group fairness notions are linearly controlled by fairness and discriminativeness of the representation. When an incompatibility exists between different fairness notions, fair and discriminative representation hits the sweet spot that approximately satisfies all notions. Motivated by our theoretical findings, we propose to learn both fair and discriminative representations using pretext loss which self-supervises learning, and Maximum Mean Discrepancy as a fair regularizer. Experiments on tabular, image, and face datasets show that using the learned representation, downstream predictions that we are unaware of when learning the representation indeed become fairer for seven group fairness notions, and the fairness guarantees computed from our theoretical results are all valid.