Thinking Outside the Box: Orthogonal Approach to Equalizing Protected Attributes

• URL: http://arxiv.org/abs/2311.14733v1
• Date: Tue, 21 Nov 2023 13:48:56 GMT
• Title: Thinking Outside the Box: Orthogonal Approach to Equalizing Protected Attributes
• Authors: Jiahui Liu, Xiaohao Cai and Mahesan Niranjan
• Abstract summary: Black box AI may exacerbate health-related disparities and biases in clinical decision-making. This work proposes a machine learning-based approach aiming to analyze and suppress the effect of the confounder.
• Score: 6.852292115526837
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: There is growing concern that the potential of black box AI may exacerbate health-related disparities and biases such as gender and ethnicity in clinical decision-making. Biased decisions can arise from data availability and collection processes, as well as from the underlying confounding effects of the protected attributes themselves. This work proposes a machine learning-based orthogonal approach aiming to analyze and suppress the effect of the confounder through discriminant dimensionality reduction and orthogonalization of the protected attributes against the primary attribute information. By doing so, the impact of the protected attributes on disease diagnosis can be realized, undesirable feature correlations can be mitigated, and the model prediction performance can be enhanced.

Related papers

• Unified Uncertainty Estimation for Cognitive Diagnosis Models [70.46998436898205]
  We propose a unified uncertainty estimation approach for a wide range of cognitive diagnosis models. We decompose the uncertainty of diagnostic parameters into data aspect and model aspect. Our method is effective and can provide useful insights into the uncertainty of cognitive diagnosis.
  arXiv  Detail & Related papers  (2024-03-09T13:48:20Z)
• Post-hoc Orthogonalization for Mitigation of Protected Feature Bias in CXR Embeddings [10.209740962369453]
  We analyze and remove protected feature effects in chest radiograph embeddings of deep learning models. Experiments reveal a significant influence of protected features on predictions of pathologies.
  arXiv  Detail & Related papers  (2023-11-02T15:59:00Z)
• Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability [82.29775890542967]
  Estimating personalized effects of treatments is a complex, yet pervasive problem. Recent developments in the machine learning literature on heterogeneous treatment effect estimation gave rise to many sophisticated, but opaque, tools. We use post-hoc feature importance methods to identify features that influence the model's predictions.
  arXiv  Detail & Related papers  (2022-06-16T17:59:05Z)
• Unlearning Protected User Attributes in Recommendations with Adversarial Training [10.268369743620159]
  Collaborative filtering algorithms capture underlying consumption patterns, including the ones specific to particular demographics or protected information of users. These encoded biases can influence the decision of a recommendation system towards further separation of the contents provided to various demographic subgroups. In this work, we investigate the possibility and challenges of removing specific protected information of users from the learned interaction representations of a RS algorithm.
  arXiv  Detail & Related papers  (2022-06-09T13:36:28Z)
• SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles [50.90773979394264]
  This paper studies a model that protects the privacy of individuals' sensitive information while also allowing it to learn non-discriminatory predictors. A key characteristic of the proposed model is to enable the adoption of off-the-selves and non-private fair models to create a privacy-preserving and fair model.
  arXiv  Detail & Related papers  (2022-04-11T14:42:54Z)
• Marrying Fairness and Explainability in Supervised Learning [0.0]
  We formalize direct discrimination as a direct causal effect of the protected attributes on the decisions. We find that state-of-the-art fair learning methods can induce discrimination via association or reverse discrimination. We propose to nullify the influence of the protected attribute on the output of the system, while preserving the influence of remaining features.
  arXiv  Detail & Related papers  (2022-04-06T17:26:58Z)
• Dikaios: Privacy Auditing of Algorithmic Fairness via Attribute Inference Attacks [0.5801044612920815]
  We propose Dikaios, a privacy auditing tool for fairness algorithms for model builders. We show that our attribute inference attacks with adaptive prediction threshold significantly outperform prior attacks.
  arXiv  Detail & Related papers  (2022-02-04T17:19:59Z)
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach [131.20444904674494]
  We tackle the problem of measuring group fairness under unawareness of sensitive attributes. We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
  arXiv  Detail & Related papers  (2021-09-17T13:45:46Z)
• 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)

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.