Counterfactual Reasoning for Bias Evaluation and Detection in a Fairness
under Unawareness setting
- URL: http://arxiv.org/abs/2302.08204v2
- Date: Sat, 26 Aug 2023 08:04:19 GMT
- Title: Counterfactual Reasoning for Bias Evaluation and Detection in a Fairness
under Unawareness setting
- Authors: Giandomenico Cornacchia, Vito Walter Anelli, Fedelucio Narducci,
Azzurra Ragone, Eugenio Di Sciascio
- Abstract summary: Current AI regulations require discarding sensitive features in the algorithm's decision-making process to prevent unfair outcomes.
We propose a way to reveal the potential hidden bias of a machine learning model that can persist even when sensitive features are discarded.
- Score: 6.004889078682389
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Current AI regulations require discarding sensitive features (e.g., gender,
race, religion) in the algorithm's decision-making process to prevent unfair
outcomes. However, even without sensitive features in the training set,
algorithms can persist in discrimination. Indeed, when sensitive features are
omitted (fairness under unawareness), they could be inferred through non-linear
relations with the so called proxy features. In this work, we propose a way to
reveal the potential hidden bias of a machine learning model that can persist
even when sensitive features are discarded. This study shows that it is
possible to unveil whether the black-box predictor is still biased by
exploiting counterfactual reasoning. In detail, when the predictor provides a
negative classification outcome, our approach first builds counterfactual
examples for a discriminated user category to obtain a positive outcome. Then,
the same counterfactual samples feed an external classifier (that targets a
sensitive feature) that reveals whether the modifications to the user
characteristics needed for a positive outcome moved the individual to the
non-discriminated group. When this occurs, it could be a warning sign for
discriminatory behavior in the decision process. Furthermore, we leverage the
deviation of counterfactuals from the original sample to determine which
features are proxies of specific sensitive information. Our experiments show
that, even if the model is trained without sensitive features, it often suffers
discriminatory biases.
Related papers
- What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning [52.51430732904994]
In reinforcement learning problems, agents must consider long-term fairness while maximizing returns.
Recent works have proposed many different types of fairness notions, but how unfairness arises in RL problems remains unclear.
We introduce a novel notion called dynamics fairness, which explicitly captures the inequality stemming from environmental dynamics.
arXiv Detail & Related papers (2024-04-16T22:47:59Z) - Towards Assumption-free Bias Mitigation [47.5131072745805]
We propose an assumption-free framework to detect the related attributes automatically by modeling feature interaction for bias mitigation.
Experimental results on four real-world datasets demonstrate that our proposed framework can significantly alleviate unfair prediction behaviors.
arXiv Detail & Related papers (2023-07-09T05:55:25Z) - Bounding Counterfactuals under Selection Bias [60.55840896782637]
We propose a first algorithm to address both identifiable and unidentifiable queries.
We prove that, in spite of the missingness induced by the selection bias, the likelihood of the available data is unimodal.
arXiv Detail & Related papers (2022-07-26T10:33:10Z) - Semi-FairVAE: Semi-supervised Fair Representation Learning with
Adversarial Variational Autoencoder [92.67156911466397]
We propose a semi-supervised fair representation learning approach based on adversarial variational autoencoder.
We use a bias-aware model to capture inherent bias information on sensitive attribute.
We also use a bias-free model to learn debiased fair representations by using adversarial learning to remove bias information from them.
arXiv Detail & Related papers (2022-04-01T15:57:47Z) - Gradient Based Activations for Accurate Bias-Free Learning [22.264226961225003]
We show that a biased discriminator can actually be used to improve this bias-accuracy tradeoff.
Specifically, this is achieved by using a feature masking approach using the discriminator's gradients.
We show that this simple approach works well to reduce bias as well as improve accuracy significantly.
arXiv Detail & Related papers (2022-02-17T00:30:40Z) - fairadapt: Causal Reasoning for Fair Data Pre-processing [2.1915057426589746]
This manuscript describes the R-package fairadapt, which implements a causal inference pre-processing method.
We discuss appropriate relaxations which assume certain causal pathways from the sensitive attribute to the outcome are not discriminatory.
arXiv Detail & Related papers (2021-10-19T18:48:28Z) - A fuzzy-rough uncertainty measure to discover bias encoded explicitly or
implicitly in features of structured pattern classification datasets [0.0]
We study the existence of bias encoded implicitly in non-protected features as defined by the correlation between protected and unprotected attributes.
We conduct a sensitivity analysis to determine the fuzzy operatorsand distance function that best capture change in the boundary regions.
arXiv Detail & Related papers (2021-08-20T10:27:32Z) - Estimating and Improving Fairness with Adversarial Learning [65.99330614802388]
We propose an adversarial multi-task training strategy to simultaneously mitigate and detect bias in the deep learning-based medical image analysis system.
Specifically, we propose to add a discrimination module against bias and a critical module that predicts unfairness within the base classification model.
We evaluate our framework on a large-scale public-available skin lesion dataset.
arXiv Detail & Related papers (2021-03-07T03:10:32Z) - Differentially Private and Fair Deep Learning: A Lagrangian Dual
Approach [54.32266555843765]
This paper studies a model that protects the privacy of the individuals sensitive information while also allowing it to learn non-discriminatory predictors.
The method relies on the notion of differential privacy and the use of Lagrangian duality to design neural networks that can accommodate fairness constraints.
arXiv Detail & Related papers (2020-09-26T10:50:33Z) - 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.