# Semi-FairVAE: Semi-supervised Fair Representation Learning with Adversarial Variational Autoencoder

arXiv: https://arxiv.org/abs/2204.00536 · HTML: https://mlsanity.com/paper/2204.00536/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 1 Apr 2022.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Empirical Risk Minimization under Fairness Constraints](https://mlsanity.com/paper/1802.08626/) (2018)
- [Fairness in Machine Learning](https://mlsanity.com/paper/2012.15816/) (2020)
- [Learning Gender-Neutral Word Embeddings](https://mlsanity.com/paper/1809.01496/) (2018)
- [Beyond Parity: Fairness Objectives for Collaborative Filtering](https://mlsanity.com/paper/1705.08804/) (2017)
- [Neural News Recommendation with Attentive Multi-View Learning](https://mlsanity.com/paper/1907.05576/) (2019)
- [Learning Fair Representations for Recommendation: A Graph-based Perspective](https://mlsanity.com/paper/2102.09140/) (2021)
- [FairRec: Fairness-aware News Recommendation with Decomposed Adversarial Learning](https://mlsanity.com/paper/2006.16742/) (2020)
- [Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination](https://mlsanity.com/paper/2009.12040/) (2020)
- [Fairness, Semi-Supervised Learning, and More: A General Framework for Clustering with Stochastic Pairwise Constraints](https://mlsanity.com/paper/2103.02013/) (2021)
- [Leveraging Semi-Supervised Learning for Fairness using Neural Networks](https://mlsanity.com/paper/1912.13230/) (2019)

## Built on by (most cited first, 5 of 5)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [A survey on bias in machine learning research](https://mlsanity.com/paper/2308.11254/) (2023)
- [Learning Fair Representations with High-Confidence Guarantees](https://mlsanity.com/paper/2310.15358/) (2023)
- [Adversarial Robustness of VAEs across Intersectional Subgroups](https://mlsanity.com/paper/2407.03864/) (2024)
- [Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference](https://mlsanity.com/paper/2510.21017/) (2025)

## Abstract (arXiv)

Adversarial learning is a widely used technique in fair representation learning to remove the biases on sensitive attributes from data representations. It usually requires to incorporate the sensitive attribute labels as prediction targets. However, in many scenarios the sensitive attribute labels of many samples can be unknown, and it is difficult to train a strong discriminator based on the scarce data with observed attribute labels, which may lead to generate unfair representations. In this paper, we propose a semi-supervised fair representation learning approach based on adversarial variational autoencoder, which can reduce the dependency of adversarial fair models on data with labeled sensitive attributes. More specifically, we use a bias-aware model to capture inherent bias information on sensitive attribute by accurately predicting sensitive attributes from input data, and we use a bias-free model to learn debiased fair representations by using adversarial learning to remove bias information from them. The hidden representations learned by the two models are regularized to be orthogonal. In addition, the soft labels predicted by the two models are further integrated into a semi-supervised variational autoencoder to reconstruct the input data, and we apply an additional entropy regularization to encourage the attribute labels inferred from the bias-free model to be high-entropy. In this way, the bias-aware model can better capture attribute information while the bias-free model is less discriminative on sensitive attributes if the input data is well reconstructed. Extensive experiments on two datasets for different tasks validate that our approach can achieve good representation learning fairness under limited data with sensitive attribute labels.