# Learning to Ignore: Fair and Task Independent Representations

arXiv: https://arxiv.org/abs/2101.04047 · HTML: https://mlsanity.com/paper/2101.04047/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 11 Jan 2021.

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

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Domain Generalization for Object Recognition with Multi-task Autoencoders](https://mlsanity.com/paper/1508.07680/) (2015)
- [Large image datasets: A pyrrhic win for computer vision?](https://mlsanity.com/paper/2006.16923/) (2020)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [Controllable Invariance through Adversarial Feature Learning](https://mlsanity.com/paper/1705.11122/) (2017)
- [Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions](https://mlsanity.com/paper/1707.06422/) (2017)
- [Invariance, Causality and Robustness](https://mlsanity.com/paper/1812.08233/) (2018)
- [Neural Network Attributions: A Causal Perspective](https://mlsanity.com/paper/1902.02302/) (2019)
- [Unsupervised Domain Adaptation with Similarity Learning](https://mlsanity.com/paper/1711.08995/) (2017)
- [Boosting Domain Adaptation by Discovering Latent Domains](https://mlsanity.com/paper/1805.01386/) (2018)
- [Transfer of Machine Learning Fairness across Domains](https://mlsanity.com/paper/1906.09688/) (2019)
- [Counterfactual Prediction with Deep Instrumental Variables Networks](https://mlsanity.com/paper/1612.09596/) (2016)
- [Controlling for Biasing Signals in Images for Prognostic Models: Survival Predictions for Lung Cancer with Deep Learning](https://mlsanity.com/paper/1904.00942/) (2019)
- [Fairness Violations and Mitigation under Covariate Shift](https://mlsanity.com/paper/1911.00677/) (2019)

## Abstract (arXiv)

Training fair machine learning models, aiming for their interpretability and solving the problem of domain shift has gained a lot of interest in the last years. There is a vast amount of work addressing these topics, mostly in separation. In this work we show that they can be seen as a common framework of learning invariant representations. The representations should allow to predict the target while at the same time being invariant to sensitive attributes which split the dataset into subgroups. Our approach is based on the simple observation that it is impossible for any learning algorithm to differentiate samples if they have the same feature representation. This is formulated as an additional loss (regularizer) enforcing a common feature representation across subgroups. We apply it to learn fair models and interpret the influence of the sensitive attribute. Furthermore it can be used for domain adaptation, transferring knowledge and learning effectively from very few examples. In all applications it is essential not only to learn to predict the target, but also to learn what to ignore.