# Back to the Drawing Board for Fair Representation Learning

arXiv: https://arxiv.org/abs/2405.18161 · HTML: https://mlsanity.com/paper/2405.18161/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 28 May 2024.

## Builds on (most cited first, 16 of 16)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [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)
- [Controllable Invariance through Adversarial Feature Learning](https://mlsanity.com/paper/1705.11122/) (2017)
- [Invariant Representations without Adversarial Training](https://mlsanity.com/paper/1805.09458/) (2018)
- [Satisfying Real-world Goals with Dataset Constraints](https://mlsanity.com/paper/1606.07558/) (2016)
- [Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation](https://mlsanity.com/paper/2101.04108/) (2021)
- [Fair Normalizing Flows](https://mlsanity.com/paper/2106.05937/) (2021)
- [Fair Representation Learning through Implicit Path Alignment](https://mlsanity.com/paper/2205.13316/) (2022)
- [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)
- [Unprocessing Seven Years of Algorithmic Fairness](https://mlsanity.com/paper/2306.07261/) (2023)

## Abstract (arXiv)

The goal of Fair Representation Learning (FRL) is to mitigate biases in machine learning models by learning data representations that enable high accuracy on downstream tasks while minimizing discrimination based on sensitive attributes. The evaluation of FRL methods in many recent works primarily focuses on the tradeoff between downstream fairness and accuracy with respect to a single task that was used to approximate the utility of representations during training (proxy task). This incentivizes retaining only features relevant to the proxy task while discarding all other information. In extreme cases, this can cause the learned representations to collapse to a trivial, binary value, rendering them unusable in transfer settings. In this work, we argue that this approach is fundamentally mismatched with the original motivation of FRL, which arises from settings with many downstream tasks unknown at training time (transfer tasks). To remedy this, we propose to refocus the evaluation protocol of FRL methods primarily around the performance on transfer tasks. A key challenge when conducting such an evaluation is the lack of adequate benchmarks. We address this by formulating four criteria that a suitable evaluation procedure should fulfill. Based on these, we propose TransFair, a benchmark that satisfies these criteria, consisting of novel variations of popular FRL datasets with carefully calibrated transfer tasks. In this setting, we reevaluate state-of-the-art FRL methods, observing that they often overfit to the proxy task, which causes them to underperform on certain transfer tasks. We further highlight the importance of task-agnostic learning signals for FRL methods, as they can lead to more transferrable representations.