# Learning Smooth and Fair Representations

arXiv: https://arxiv.org/abs/2006.08788 · HTML: https://mlsanity.com/paper/2006.08788/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2020.

## Built on by (most cited first, 12 of 12)

- [FARE: Provably Fair Representation Learning with Practical Certificates](https://mlsanity.com/paper/2210.07213/) (2022)
- [Learning fair representation with a parametric integral probability metric](https://mlsanity.com/paper/2202.02943/) (2022)
- [Latent Space Smoothing for Individually Fair Representations](https://mlsanity.com/paper/2111.13650/) (2021)
- [Fair Representations by Compression](https://mlsanity.com/paper/2105.14044/) (2021)
- [Disentangled Representation with Causal Constraints for Counterfactual Fairness](https://mlsanity.com/paper/2208.09147/) (2022)
- [Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics](https://mlsanity.com/paper/2505.06435/) (2025)
- [Ultra-marginal Feature Importance: Learning from Data with Causal Guarantees](https://mlsanity.com/paper/2204.09938/) (2022)
- [SoFaiR: Single Shot Fair Representation Learning](https://mlsanity.com/paper/2204.12556/) (2022)
- [Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and R'enyi Measures](https://mlsanity.com/paper/2206.10043/) (2022)
- [Learning Fair Representations with High-Confidence Guarantees](https://mlsanity.com/paper/2310.15358/) (2023)
- [Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference](https://mlsanity.com/paper/2510.21017/) (2025)
- [Fair Model-based Clustering](https://mlsanity.com/paper/2602.21509/) (2026)

## Abstract (arXiv)

Organizations that own data face increasing legal liability for its discriminatory use against protected demographic groups, extending to contractual transactions involving third parties access and use of the data. This is problematic, since the original data owner cannot ex-ante anticipate all its future uses by downstream users. This paper explores the upstream ability to preemptively remove the correlations between features and sensitive attributes by mapping features to a fair representation space. Our main result shows that the fairness measured by the demographic parity of the representation distribution can be certified from a finite sample if and only if the chi-squared mutual information between features and representations is finite. Empirically, we find that smoothing the representation distribution provides generalization guarantees of fairness certificates, which improves upon existing fair representation learning approaches. Moreover, we do not observe that smoothing the representation distribution degrades the accuracy of downstream tasks compared to state-of-the-art methods in fair representation learning.