Learning from Discriminatory Training Data
- URL: http://arxiv.org/abs/1912.08189v4
- Date: Fri, 21 Apr 2023 02:31:12 GMT
- Title: Learning from Discriminatory Training Data
- Authors: Przemyslaw A. Grabowicz, Nicholas Perello, Kenta Takatsu
- Abstract summary: Supervised learning systems are trained using historical data and, if the data was tainted by discrimination, they may unintentionally learn to discriminate against protected groups.
We propose that fair learning methods, despite training on potentially discriminatory datasets, shall perform well on fair test datasets.
- Score: 2.1869017389979266
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Supervised learning systems are trained using historical data and, if the
data was tainted by discrimination, they may unintentionally learn to
discriminate against protected groups. We propose that fair learning methods,
despite training on potentially discriminatory datasets, shall perform well on
fair test datasets. Such dataset shifts crystallize application scenarios for
specific fair learning methods. For instance, the removal of direct
discrimination can be represented as a particular dataset shift problem. For
this scenario, we propose a learning method that provably minimizes model error
on fair datasets, while blindly training on datasets poisoned with direct
additive discrimination. The method is compatible with existing legal systems
and provides a solution to the widely discussed issue of protected groups'
intersectionality by striking a balance between the protected groups.
Technically, the method applies probabilistic interventions, has causal and
counterfactual formulations, and is computationally lightweight - it can be
used with any supervised learning model to prevent discrimination via proxies
while maximizing model accuracy for business necessity.
Related papers
- Fairness Without Harm: An Influence-Guided Active Sampling Approach [32.173195437797766]
We aim to train models that mitigate group fairness disparity without causing harm to model accuracy.
The current data acquisition methods, such as fair active learning approaches, typically require annotating sensitive attributes.
We propose a tractable active data sampling algorithm that does not rely on training group annotations.
arXiv Detail & Related papers (2024-02-20T07:57:38Z) - Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning [69.81438976273866]
Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers)
We introduce evidential deep learning (EDL) as an outlier detector to quantify different types of uncertainty, and design different uncertainty metrics for self-training and inference.
We propose a novel adaptive negative optimization strategy, making EDL more tailored to the unlabeled dataset containing both inliers and outliers.
arXiv Detail & Related papers (2023-03-21T09:07:15Z) - Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions [13.279926364884512]
Machine learning models can underperform on certain population groups due to choices made during model development and bias inherent in the data.
We quantify aleatoric discrimination by determining the performance limits of a model under fairness constraints.
We quantify epistemic discrimination as the gap between a model's accuracy when fairness constraints are applied and the limit posed by aleatoric discrimination.
arXiv Detail & Related papers (2023-01-27T15:38:20Z) - Canary in a Coalmine: Better Membership Inference with Ensembled
Adversarial Queries [53.222218035435006]
We use adversarial tools to optimize for queries that are discriminative and diverse.
Our improvements achieve significantly more accurate membership inference than existing methods.
arXiv Detail & Related papers (2022-10-19T17:46:50Z) - Revealing Unfair Models by Mining Interpretable Evidence [50.48264727620845]
The popularity of machine learning has increased the risk of unfair models getting deployed in high-stake applications.
In this paper, we tackle the novel task of revealing unfair models by mining interpretable evidence.
Our method finds highly interpretable and solid evidence to effectively reveal the unfairness of trained models.
arXiv Detail & Related papers (2022-07-12T20:03:08Z) - CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time.
We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
arXiv Detail & Related papers (2022-06-01T03:02:07Z) - Statistical discrimination in learning agents [64.78141757063142]
Statistical discrimination emerges in agent policies as a function of both the bias in the training population and of agent architecture.
We show that less discrimination emerges with agents that use recurrent neural networks, and when their training environment has less bias.
arXiv Detail & Related papers (2021-10-21T18:28:57Z) - Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce
Discrimination [53.3082498402884]
A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair.
We present a framework of fair semi-supervised learning in the pre-processing phase, including pseudo labeling to predict labels for unlabeled data.
A theoretical decomposition analysis of bias, variance and noise highlights the different sources of discrimination and the impact they have on fairness in semi-supervised learning.
arXiv Detail & Related papers (2020-09-25T05:48:56Z) - On Adversarial Bias and the Robustness of Fair Machine Learning [11.584571002297217]
We show that giving the same importance to groups of different sizes and distributions, to counteract the effect of bias in training data, can be in conflict with robustness.
An adversary who can control sampling or labeling for a fraction of training data, can reduce the test accuracy significantly beyond what he can achieve on unconstrained models.
We analyze the robustness of fair machine learning through an empirical evaluation of attacks on multiple algorithms and benchmark datasets.
arXiv Detail & Related papers (2020-06-15T18:17:44Z) - Fairness-Aware Learning with Prejudice Free Representations [2.398608007786179]
We propose a novel algorithm that can effectively identify and treat latent discriminating features.
The approach helps to collect discrimination-free features that would improve the model performance.
arXiv Detail & Related papers (2020-02-26T10:06:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.