Unbiased Model Prediction Without Using Protected Attribute Information

• URL: http://arxiv.org/abs/2603.29270v2
• Date: Sun, 05 Apr 2026 10:19:32 GMT
• Title: Unbiased Model Prediction Without Using Protected Attribute Information
• Abstract summary: We propose a novel algorithm, termed as textbfNon-Protected Attribute-based Debiasing (NPAD) algorithm for bias mitigation, that does not require the protected attribute information.<n>The proposed NPAD algorithm utilizes the auxiliary information provided by the non-protected attributes to optimize the model for bias mitigation.
• Score: 33.78162609357593
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The problem of bias persists in the deep learning community as models continue to provide disparate performance across different demographic subgroups. Therefore, several algorithms have been proposed to improve the fairness of deep models. However, a majority of these algorithms utilize the protected attribute information for bias mitigation, which severely limits their application in real-world scenarios. To address this concern, we have proposed a novel algorithm, termed as \textbf{Non-Protected Attribute-based Debiasing (NPAD)} algorithm for bias mitigation, that does not require the protected attribute information. The proposed NPAD algorithm utilizes the auxiliary information provided by the non-protected attributes to optimize the model for bias mitigation. Further, two different loss functions, \textbf{Debiasing via Attribute Cluster Loss (DACL)} and \textbf{Filter Redundancy Loss (FRL)} have been proposed to optimize the model for fairness goals. Multiple experiments are performed on the LFWA and CelebA datasets for facial attribute prediction, and a significant reduction in bias across different gender and age subgroups is observed.

Related papers

• Preference Data Selection for Mitigating the Alignment Tax in Large Language Models [52.18310687523229]
  BALIGN is a balanced data selection strategy that mitigates catastrophic forgetting while optimizing alignment efficacy.<n>By aggregating three key data-centric features into a unified composite risk score, BALIGN systematically filters out high-risk preference samples.<n>Experiments on standard human preference datasets demonstrate that BALIGN strongly preserves foundational capabilities without compromising alignment gains.
  arXiv  Detail & Related papers  (2026-08-25T07:58:42Z)
• Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains [67.71020482405343]
  We study how to design algorithms that can leverage additional information in the form of rating gap.<n>We present new algorithms that can achieve faster statistical rates than DPO in presence of accurate rating gap information.
  arXiv  Detail & Related papers  (2026-01-31T08:38:21Z)
• Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Clipping Bias and Remedies [28.699424769503764]
  This paper studies the convergence of clipped gradient descent (SGD) algorithms with decision-dependent data distribution.<n>We characterize clipping bias with clipped (PCSGD) which is caused by clipping operator that prevents SGDGD from reaching a stable solution.<n>Our analysis is also extended to show that the latter algorithm is free from clipping bias in the performative setting.
  arXiv  Detail & Related papers  (2024-04-17T02:17:05Z)
• 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)
• Causality and Independence Enhancement for Biased Node Classification [56.38828085943763]
  We propose a novel Causality and Independence Enhancement (CIE) framework, applicable to various graph neural networks (GNNs) Our approach estimates causal and spurious features at the node representation level and mitigates the influence of spurious correlations. Our approach CIE not only significantly enhances the performance of GNNs but outperforms state-of-the-art debiased node classification methods.
  arXiv  Detail & Related papers  (2023-10-14T13:56:24Z)
• Fairness via Adversarial Attribute Neighbourhood Robust Learning [49.93775302674591]
  We propose a principled underlineRobust underlineAdversarial underlineAttribute underlineNeighbourhood (RAAN) loss to debias the classification head.
  arXiv  Detail & Related papers  (2022-10-12T23:39:28Z)
• Fair mapping [0.0]
  We propose a novel pre-processing method based on the transformation of the distribution of protected groups onto a chosen target one. We leverage on the recent works of the Wasserstein GAN and AttGAN frameworks to achieve the optimal transport of data points. Our proposed approach, preserves the interpretability of data and can be used without defining exactly the sensitive groups.
  arXiv  Detail & Related papers  (2022-09-01T17:31:27Z)
• Mitigating Algorithmic Bias with Limited Annotations [65.060639928772]
  When sensitive attributes are not disclosed or available, it is needed to manually annotate a small part of the training data to mitigate bias. We propose Active Penalization Of Discrimination (APOD), an interactive framework to guide the limited annotations towards maximally eliminating the effect of algorithmic bias. APOD shows comparable performance to fully annotated bias mitigation, which demonstrates that APOD could benefit real-world applications when sensitive information is limited.
  arXiv  Detail & Related papers  (2022-07-20T16:31:19Z)
• 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)
• xFAIR: Better Fairness via Model-based Rebalancing of Protected Attributes [15.525314212209564]
  Machine learning software can generate models that inappropriately discriminate against specific protected social groups. We propose xFAIR, a model-based extrapolation method, that is capable of both mitigating bias and explaining the cause.
  arXiv  Detail & Related papers  (2021-10-03T22:10:14Z)
• Balancing Biases and Preserving Privacy on Balanced Faces in the Wild [50.915684171879036]
  There are demographic biases present in current facial recognition (FR) models. We introduce our Balanced Faces in the Wild dataset to measure these biases across different ethnic and gender subgroups. We find that relying on a single score threshold to differentiate between genuine and imposters sample pairs leads to suboptimal results. We propose a novel domain adaptation learning scheme that uses facial features extracted from state-of-the-art neural networks.
  arXiv  Detail & Related papers  (2021-03-16T15:05:49Z)

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.