# Fairness without the sensitive attribute via Causal Variational Autoencoder

arXiv: https://arxiv.org/abs/2109.04999 · HTML: https://mlsanity.com/paper/2109.04999/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 10 Sep 2021.

## Builds on (most cited first, 23 of 23)

- [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)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Ladder Variational Autoencoders](https://mlsanity.com/paper/1602.02282/) (2016)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Variational Lossy Autoencoder](https://mlsanity.com/paper/1611.02731/) (2016)
- [Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees](https://mlsanity.com/paper/1806.06055/) (2018)
- [InfoVAE: Information Maximizing Variational Autoencoders](https://mlsanity.com/paper/1706.02262/) (2017)
- [Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved](https://mlsanity.com/paper/1811.11154/) (2018)
- [Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction](https://mlsanity.com/paper/1807.00199/) (2018)
- [Blind Justice: Fairness with Encrypted Sensitive Attributes](https://mlsanity.com/paper/1806.03281/) (2018)
- [Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities](https://mlsanity.com/paper/2102.04257/) (2021)
- [Transfer of Machine Learning Fairness across Domains](https://mlsanity.com/paper/1906.09688/) (2019)
- [Proxy Fairness](https://mlsanity.com/paper/1806.11212/) (2018)
- [Counterfactual Reasoning for Fair Clinical Risk Prediction](https://mlsanity.com/paper/1907.06260/) (2019)
- [Learning Unbiased Representations via R'enyi Minimization](https://mlsanity.com/paper/2009.03183/) (2020)
- [Adversarial Learning for Counterfactual Fairness](https://mlsanity.com/paper/2008.13122/) (2020)

## Built on by (most cited first, 21 of 21)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Improving Fairness in Deepfake Detection](https://mlsanity.com/paper/2306.16635/) (2023)
- [FairMask: Better Fairness via Model-based Rebalancing of Protected Attributes](https://mlsanity.com/paper/2110.01109/) (2021)
- [Towards Counterfactual Fairness-aware Domain Generalization in Changing Environments](https://mlsanity.com/paper/2309.13005/) (2023)
- [A Fair Pricing Model via Adversarial Learning](https://mlsanity.com/paper/2202.12008/) (2022)
- [Learning Fair Models without Sensitive Attributes: A Generative Approach](https://mlsanity.com/paper/2203.16413/) (2022)
- [Fairness without Sensitive Attributes via Knowledge Sharing](https://mlsanity.com/paper/2409.18470/) (2024)
- [Manifestations of Xenophobia in AI Systems](https://mlsanity.com/paper/2212.07877/) (2022)
- [Fairness without Demographics through Learning Graph of Gradients](https://mlsanity.com/paper/2412.03706/) (2024)
- [A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis](https://mlsanity.com/paper/2210.04491/) (2022)
- [AI-Driven Healthcare: A Review on Ensuring Fairness and Mitigating Bias](https://mlsanity.com/paper/2407.19655/) (2024)
- [Fair Recommendations with Limited Sensitive Attributes: A Distributionally Robust Optimization Approach](https://mlsanity.com/paper/2405.01063/) (2024)
- [Cherry on the Cake: Fairness is NOT an Optimization Problem](https://mlsanity.com/paper/2406.16606/) (2024)
- [Contagion Effect Estimation Using Proximal Embeddings](https://mlsanity.com/paper/2306.02479/) (2023)
- [Towards Harmless Rawlsian Fairness Regardless of Demographic Prior](https://mlsanity.com/paper/2411.02467/) (2024)
- [Demographic-Agnostic Fairness without Harm](https://mlsanity.com/paper/2509.24077/) (2025)
- [Fairness-Aware Graph Representation Learning with Limited Demographic Information](https://mlsanity.com/paper/2511.13540/) (2025)
- [Safe Fairness Guarantees Without Demographics in Classification: Spectral Uncertainty Set Perspective](https://mlsanity.com/paper/2602.11785/) (2026)
- [Alpha and Prejudice: Improving α-sized Worst-case Fairness via Intrinsic Reweighting](https://mlsanity.com/paper/2411.03068/) (2024)
- [Fairness Constraints in High-Dimensional Generalized Linear Models](https://mlsanity.com/paper/2604.16610/) (2026)
- [A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes](https://mlsanity.com/paper/2608.10470/) (2026)

## Abstract (arXiv)

In recent years, most fairness strategies in machine learning models focus on mitigating unwanted biases by assuming that the sensitive information is observed. However this is not always possible in practice. Due to privacy purposes and var-ious regulations such as RGPD in EU, many personal sensitive attributes are frequently not collected. We notice a lack of approaches for mitigating bias in such difficult settings, in particular for achieving classical fairness objectives such as Demographic Parity and Equalized Odds. By leveraging recent developments for approximate inference, we propose an approach to fill this gap. Based on a causal graph, we rely on a new variational auto-encoding based framework named SRCVAE to infer a sensitive information proxy, that serve for bias mitigation in an adversarial fairness approach. We empirically demonstrate significant improvements over existing works in the field. We observe that the generated proxy's latent space recovers sensitive information and that our approach achieves a higher accuracy while obtaining the same level of fairness on two real datasets, as measured using com-mon fairness definitions.