MESD: Detecting and Mitigating Procedural Bias in Intersectional Groups

• URL: http://arxiv.org/abs/2603.13452v1
• Date: Fri, 13 Mar 2026 15:42:31 GMT
• Title: MESD: Detecting and Mitigating Procedural Bias in Intersectional Groups
• Abstract summary: This research addresses an important gap by examining explainability with respect to fairness across multiple protected categories.<n> Experimental results across multiple datasets show that UEF effectively balances objectives.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Research about bias in machine learning has mostly focused on outcome-oriented fairness metrics (e.g., equalized odds) and on a single protected category. Although these approaches offer great insight into bias in ML, they provide limited insight into model procedure bias. To address this gap, we proposed multi-category explanation stability disparity (MESD), an intersectional, procedurally oriented metric that measures the disparity in the quality of explanations across intersectional subgroups in multiple protected categories. MESD serves as a complementary metric to outcome-oriented metrics, providing detailed insight into the procedure of a model. To further extend the scope of the holistic selection model, we also propose a multi-objective optimization framework, UEF (Utility-Explanation-Fairness), that jointly optimizes three objectives. Experimental results across multiple datasets show that UEF effectively balances objectives. Also, the results show that MESD can effectively capture the explanation difference between intersectional groups. This research addresses an important gap by examining explainability with respect to fairness across multiple protected categories.

Related papers

• FairSelect: A Systematic Evaluation of Multi-Level and Intersectional Algorithmic Fairness [0.5295211483828045]
  Algorithmic fairness methods are increasingly used to identify and mitigate bias in machine learning models.<n>This work presents FairSelect, a toolkit for evaluating fairness mitigation strategies applied individually and in combination.
  arXiv  Detail & Related papers  (2026-07-09T21:27:29Z)
• GESD: Beyond Outcome-Oriented Fairness [0.0]
  Group-level Explanation Stability Disparity (GESD) is a fairness metric that measures disparities in the stability, robustness, and sensitivity of model explanations.<n>Our code and datasets are available on GitHub.
  arXiv  Detail & Related papers  (2026-05-14T18:10:57Z)
• SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning [50.93295951454092]
  We introduce a set level diversity objective defined over sampled trajectories using kernelized similarity.<n>Our approach derives a leave-one-out marginal contribution for each sampled trajectory and integrates this objective as a plug-in advantage shaping term for policy optimization.<n>Experiments across a range of model scales demonstrate the effectiveness of our proposed algorithm, consistently outperforming strong baselines in both Pass@1 and Pass@K across various benchmarks.
  arXiv  Detail & Related papers  (2026-02-01T07:13:20Z)
• FAIRWELL: Fair Multimodal Self-Supervised Learning for Wellbeing Prediction [16.913286294651236]
  We propose a novel subject-level loss function to learn fairer representations via the following three mechanisms.<n>We evaluate our method on three challenging real-world heterogeneous healthcare datasets.
  arXiv  Detail & Related papers  (2025-08-22T19:03:06Z)
• Fairness at Every Intersection: Uncovering and Mitigating Intersectional Biases in Multimodal Clinical Predictions [17.578593616991927]
  We take the initial steps to uncover potential intersectional biases in predictions by sourcing extensive multimodal datasets.<n>We perform and benchmark downstream tasks and bias evaluation on the datasets by learning a unified text representation from multimodal sources.<n>Our findings indicate that the proposed sub-group-specific bias mitigation is robust across different datasets.
  arXiv  Detail & Related papers  (2024-11-30T22:53:11Z)
• Deriving Causal Order from Single-Variable Interventions: Guarantees & Algorithm [14.980926991441345]
  We show that datasets containing interventional data can be effectively extracted under realistic assumptions about the data distribution.<n>We introduce a novel variant of interventional faithfulness, which relies on comparisons between the marginal distributions of each variable across observational and interventional settings.<n>We also introduce Intersort, an algorithm designed to infer the causal order from datasets containing large numbers of single-variable interventions.
  arXiv  Detail & Related papers  (2024-05-28T16:07:17Z)
• Does Machine Bring in Extra Bias in Learning? Approximating Fairness in Models Promptly [2.002741592555996]
  Existing techniques for assessing the discrimination level of machine learning models include commonly used group and individual fairness measures. We propose a "harmonic fairness measure via manifold (HFM)" based on distances between sets. Empirical results indicate that the proposed fairness measure HFM is valid and that the proposed ApproxDist is effective and efficient.
  arXiv  Detail & Related papers  (2024-05-15T11:07:40Z)
• Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data [102.16105233826917]
  Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and contrastive learning.
  arXiv  Detail & Related papers  (2024-04-22T17:20:18Z)
• A structured regression approach for evaluating model performance across intersectional subgroups [53.91682617836498]
  Disaggregated evaluation is a central task in AI fairness assessment, where the goal is to measure an AI system's performance across different subgroups. We introduce a structured regression approach to disaggregated evaluation that we demonstrate can yield reliable system performance estimates even for very small subgroups.
  arXiv  Detail & Related papers  (2024-01-26T14:21:45Z)
• MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
  Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition. We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL) In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
  arXiv  Detail & Related papers  (2021-07-23T06:57:08Z)
• Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation [51.93711960601973]
  We propose a novel margin preserving self-paced contrastive Learning model for cross-modal medical image segmentation. With the guidance of progressively refined semantic prototypes, a novel margin preserving contrastive loss is proposed to boost the discriminability of embedded representation space. Experiments on cross-modal cardiac segmentation tasks demonstrate that MPSCL significantly improves semantic segmentation performance.
  arXiv  Detail & Related papers  (2021-03-15T15:23:10Z)
• Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility [54.179859639868646]
  Bipartite ranking aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data. There have been rising concerns on whether the learned scoring function can cause systematic disparity across different protected groups. We propose a model post-processing framework for balancing them in the bipartite ranking scenario.
  arXiv  Detail & Related papers  (2020-06-15T10:08:39Z)
• Addressing multiple metrics of group fairness in data-driven decision making [2.750586731051391]
  FAT-ML literature proposes a varied set of group fairness metrics to measure discrimination against socio-demographic groups. We observe that several of these metrics cluster together in two or three main clusters for the same groups and machine learning methods. We propose a robust way to visualize multidimensional fairness in two dimensions through a Principal Component Analysis (PCA) of the group fairness metrics.
  arXiv  Detail & Related papers  (2020-03-10T15:13:05Z)

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.