# Unfairness Discovery and Prevention For Few-Shot Regression

arXiv: https://arxiv.org/abs/2009.11406 · HTML: https://mlsanity.com/paper/2009.11406/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2020.

## Built on by (most cited first, 10 of 10)

- [Fairness-Aware Online Meta-learning](https://mlsanity.com/paper/2108.09435/) (2021)
- [CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models](https://mlsanity.com/paper/2407.02408/) (2024)
- [Adaptive Fairness-Aware Online Meta-Learning for Changing Environments](https://mlsanity.com/paper/2205.11264/) (2022)
- [Towards Fair Disentangled Online Learning for Changing Environments](https://mlsanity.com/paper/2306.01007/) (2023)
- [Towards Counterfactual Fairness-aware Domain Generalization in Changing Environments](https://mlsanity.com/paper/2309.13005/) (2023)
- [Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously](https://mlsanity.com/paper/2311.13816/) (2023)
- [Fair Regression under Sample Selection Bias](https://mlsanity.com/paper/2110.04372/) (2021)
- [A Survey on Preserving Fairness Guarantees in Changing Environments](https://mlsanity.com/paper/2211.07530/) (2022)
- [Fair Few-shot Learning with Auxiliary Sets](https://mlsanity.com/paper/2308.14338/) (2023)
- [Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness](https://mlsanity.com/paper/2402.12319/) (2024)

## Abstract (arXiv)

We study fairness in supervised few-shot meta-learning models that are sensitive to discrimination (or bias) in historical data. A machine learning model trained based on biased data tends to make unfair predictions for users from minority groups. Although this problem has been studied before, existing methods mainly aim to detect and control the dependency effect of the protected variables (e.g. race, gender) on target prediction based on a large amount of training data. These approaches carry two major drawbacks that (1) lacking showing a global cause-effect visualization for all variables; (2) lacking generalization of both accuracy and fairness to unseen tasks. In this work, we first discover discrimination from data using a causal Bayesian knowledge graph which not only demonstrates the dependency of the protected variable on target but also indicates causal effects between all variables. Next, we develop a novel algorithm based on risk difference in order to quantify the discriminatory influence for each protected variable in the graph. Furthermore, to protect prediction from unfairness, a fast-adapted bias-control approach in meta-learning is proposed, which efficiently mitigates statistical disparity for each task and it thus ensures independence of protected attributes on predictions based on biased and few-shot data samples. Distinct from existing meta-learning models, group unfairness of tasks are efficiently reduced by leveraging the mean difference between (un)protected groups for regression problems. Through extensive experiments on both synthetic and real-world data sets, we demonstrate that our proposed unfairness discovery and prevention approaches efficiently detect discrimination and mitigate biases on model output as well as generalize both accuracy and fairness to unseen tasks with a limited amount of training samples.