Procedural Fairness via Group Counterfactual Explanation

• URL: http://arxiv.org/abs/2603.11140v1
• Date: Wed, 11 Mar 2026 16:38:59 GMT
• Title: Procedural Fairness via Group Counterfactual Explanation
• Abstract summary: Group Counterfactual Integrated Gradients (GCIG) is an in-processing regularization framework that enforces explanation invariance across groups.<n>We show that GCIG substantially reduces cross-group explanation disparity while maintaining competitive predictive performance.<n>Our results also show that aligning model reasoning across groups offers a principled and practical avenue for advancing fairness beyond outcome parity.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fairness in machine learning research has largely focused on outcome-oriented fairness criteria such as Equalized Odds, while comparatively less attention has been given to procedural-oriented fairness, which addresses how a model arrives at its predictions. Neglecting procedural fairness means it is possible for a model to generate different explanations for different protected groups, thereby eroding trust. In this work, we introduce Group Counterfactual Integrated Gradients (GCIG), an in-processing regularization framework that enforces explanation invariance across groups, conditioned on the true label. For each input, GCIG computes explanations relative to multiple Group Conditional baselines and penalizes cross-group variation in these attributions during training. GCIG formalizes procedural fairness as Group Counterfactual explanation stability and complements existing fairness objectives that constrain predictions alone. We compared GCIG empirically against six state-of-the-art methods, and the results show that GCIG substantially reduces cross-group explanation disparity while maintaining competitive predictive performance and accuracy-fairness trade-offs. Our results also show that aligning model reasoning across groups offers a principled and practical avenue for advancing fairness beyond outcome parity.

Related papers

• Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization [2.6245086561385276]
  We propose an end-to-end Mixture-of-Experts (MoE) framework that corrects subgroup imbalance.<n>We apply subgroup reweighting to correct data imbalance, and introduce gate entropy regularization to prevent routing from collapsing onto subgroup attributes.<n> Experimental results demonstrate that the proposed approach improves fairness while maintaining competitive predictive performance.
  arXiv  Detail & Related papers  (2026-08-24T05:34:25Z)
• Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models [49.094293060279675]
  We introduce a new fairness definition for generative models, termed as equalized generative treatment (EGT)<n>EGT requires comparable generation quality across all sensitive groups, with quality measured via a reference f-divergence.<n>We show that min-max methods consistently achieve fairer outcomes compared to other approaches from the literature.
  arXiv  Detail & Related papers  (2026-02-09T13:52:36Z)
• On the use of graph models to achieve individual and group fairness [0.6299766708197883]
  We provide a theoretical framework based on Sheaf Diffusion to leverage tools based on dynamical systems and homology to model fairness.<n>We present a collection of network topologies handling different fairness metrics, leading to a unified method capable of dealing with both individual and group bias.<n>The paper showcases the performance of the proposed models in terms of accuracy and fairness.
  arXiv  Detail & Related papers  (2026-01-13T18:17:43Z)
• FACEGroup: Feasible and Actionable Counterfactual Explanations for Group Fairness [6.453283750455735]
  This paper introduces the first graph-based framework for generating group counterfactual explanations to audit group fairness.<n>Our framework, FACEGroup, models real-world feasibility constraints, identifies subgroups with similar counterfactuals, and captures key trade-offs in counterfactual generation.
  arXiv  Detail & Related papers  (2024-10-29T23:10:01Z)
• Fairness-Aware Meta-Learning via Nash Bargaining [63.44846095241147]
  We introduce a two-stage meta-learning framework to address issues of group-level fairness in machine learning. The first stage involves the use of a Nash Bargaining Solution (NBS) to resolve hypergradient conflicts and steer the model. We show empirical effects across various fairness objectives in six key fairness datasets and two image classification tasks.
  arXiv  Detail & Related papers  (2024-06-11T07:34:15Z)
• FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods [84.1077756698332]
  This paper introduces the Fair Fairness Benchmark (textsfFFB), a benchmarking framework for in-processing group fairness methods. We provide a comprehensive analysis of state-of-the-art methods to ensure different notions of group fairness.
  arXiv  Detail & Related papers  (2023-06-15T19:51:28Z)
• DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision [73.80009454050858]
  This work presents a self-supervised model, called DualFair, that can debias sensitive attributes like gender and race from learned representations. Our model jointly optimize for two fairness criteria - group fairness and counterfactual fairness.
  arXiv  Detail & Related papers  (2023-03-15T07:13:54Z)
• Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective [50.093280002375984]
  Performance unfairness among variables widely exists in multivariate time series (MTS) forecasting models. We propose a novel framework, named FairFor, for fairness-aware MTS forecasting.
  arXiv  Detail & Related papers  (2023-01-27T04:54:12Z)
• Unified Group Fairness on Federated Learning [22.143427873780404]
  Federated learning (FL) has emerged as an important machine learning paradigm where a global model is trained based on private data from distributed clients. Recent researches focus on achieving fairness among clients, but they ignore the fairness towards different groups formed by sensitive attribute(s) (e.g., gender and/or race) We propose a novel FL algorithm, named Group Distributionally Robust Federated Averaging (G-DRFA), which mitigates the distribution shift across groups with theoretical analysis of convergence rate.
  arXiv  Detail & Related papers  (2021-11-09T08:21:38Z)
• GroupifyVAE: from Group-based Definition to VAE-based Unsupervised Representation Disentanglement [91.9003001845855]
  VAE-based unsupervised disentanglement can not be achieved without introducing other inductive bias. We address VAE-based unsupervised disentanglement by leveraging the constraints derived from the Group Theory based definition as the non-probabilistic inductive bias. We train 1800 models covering the most prominent VAE-based models on five datasets to verify the effectiveness of our method.
  arXiv  Detail & Related papers  (2021-02-20T09:49:51Z)
• FACT: A Diagnostic for Group Fairness Trade-offs [23.358566041117083]
  Group fairness is a class of fairness notions that measure how different groups of individuals are treated differently according to their protected attributes. We propose a general diagnostic that enables systematic characterization of these trade-offs in group fairness.
  arXiv  Detail & Related papers  (2020-04-07T14:15:51Z)

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.