Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective

• URL: http://arxiv.org/abs/2506.07861v1
• Date: Mon, 09 Jun 2025 15:24:56 GMT
• Title: Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective
• Authors: Firas Laakom, Haobo Chen, Jürgen Schmidhuber, Yuheng Bu,
• Abstract summary: This paper proposes a theoretical framework for analyzing fairness generalization error through an information-theoretic lens.<n>Our empirical results validate the tightness and practical relevance of these bounds across diverse fairness-aware learning algorithms.
• Score: 28.68227117674221
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite substantial progress in promoting fairness in high-stake applications using machine learning models, existing methods often modify the training process, such as through regularizers or other interventions, but lack formal guarantees that fairness achieved during training will generalize to unseen data. Although overfitting with respect to prediction performance has been extensively studied, overfitting in terms of fairness loss has received far less attention. This paper proposes a theoretical framework for analyzing fairness generalization error through an information-theoretic lens. Our novel bounding technique is based on Efron-Stein inequality, which allows us to derive tight information-theoretic fairness generalization bounds with both Mutual Information (MI) and Conditional Mutual Information (CMI). Our empirical results validate the tightness and practical relevance of these bounds across diverse fairness-aware learning algorithms. Our framework offers valuable insights to guide the design of algorithms improving fairness generalization.

Related papers

• General Post-Processing Framework for Fairness Adjustment of Machine Learning Models [0.0]
  This paper introduces a novel framework for fairness adjustments that applies to diverse machine learning tasks.<n>By decoupling fairness adjustments from the model training process, our framework preserves model performance on average.<n>We demonstrate the effectiveness of this approach by comparing it to Adversarial Debiasing, showing that our framework achieves a comparable fairness/accuracy tradeoff on real-world datasets.
  arXiv  Detail & Related papers  (2025-04-22T20:06:59Z)
• Deep Fair Learning: A Unified Framework for Fine-tuning Representations with Sufficient Networks [8.616743904155419]
  We propose a framework that integrates sufficient dimension reduction with deep learning to construct fair and informative representations.<n>By introducing a novel penalty term during fine-tuning, our method enforces conditional independence between sensitive attributes and learned representations.<n>Our approach achieves a superior balance between fairness and utility, significantly outperforming state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-04-08T22:24:22Z)
• Impact of Data Distribution on Fairness Guarantees in Equitable Deep Learning [24.911440326496574]
  We present a theoretical framework analyzing the relationship between data distributions and fairness guarantees in equitable deep learning.<n>We derive comprehensive theoretical bounds for fairness errors and convergence rates, and characterize how distributional differences between groups affect the fundamental trade-off between fairness and accuracy.<n>This work advances our understanding of fairness in AI-based diagnosis systems and provides a theoretical foundation for developing more equitable algorithms.
  arXiv  Detail & Related papers  (2024-12-29T06:43:43Z)
• Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium [0.3350491650545292]
  Current methods for mitigating bias often result in information loss and an inadequate balance between accuracy and fairness. We propose a novel methodology grounded in bilevel optimization principles. Our deep learning-based approach concurrently optimize for both accuracy and fairness objectives.
  arXiv  Detail & Related papers  (2024-10-21T18:53:39Z)
• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• Learning for Counterfactual Fairness from Observational Data [62.43249746968616]
  Fairness-aware machine learning aims to eliminate biases of learning models against certain subgroups described by certain protected (sensitive) attributes such as race, gender, and age. A prerequisite for existing methods to achieve counterfactual fairness is the prior human knowledge of the causal model for the data. In this work, we address the problem of counterfactually fair prediction from observational data without given causal models by proposing a novel framework CLAIRE.
  arXiv  Detail & Related papers  (2023-07-17T04:08:29Z)
• Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics [80.07271410743806]
  We study the relationship between cross-domain learning (CD) and model fairness. We introduce a benchmark on face and medical images spanning several demographic groups as well as classification and localization tasks. Our study covers 14 CD approaches alongside three state-of-the-art fairness algorithms and shows how the former can outperform the latter.
  arXiv  Detail & Related papers  (2023-03-25T09:34:05Z)
• Individual Fairness under Uncertainty [26.183244654397477]
  Algorithmic fairness is an established area in machine learning (ML) algorithms. We propose an individual fairness measure and a corresponding algorithm that deal with the challenges of uncertainty arising from censorship in class labels. We argue that this perspective represents a more realistic model of fairness research for real-world application deployment.
  arXiv  Detail & Related papers  (2023-02-16T01:07:58Z)
• Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes [70.6326967720747]
  It is important to guarantee that machine learning algorithms deployed in the real world do not result in unfairness or unintended social consequences. We introduce FairCOCCO, a fairness measure built on cross-covariance operators on reproducing kernel Hilbert Spaces. We empirically demonstrate consistent improvements against state-of-the-art techniques in balancing predictive power and fairness on real-world datasets.
  arXiv  Detail & Related papers  (2022-11-11T11:28:46Z)
• Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity [61.05259660910437]
  We propose a global consistency and complementarity network (CoCoNet) to learn representations from multiple views. On the global stage, we reckon that the crucial knowledge is implicitly shared among views, and enhancing the encoder to capture such knowledge can improve the discriminability of the learned representations. Lastly on the local stage, we propose a complementarity-factor, which joints cross-view discriminative knowledge, and it guides the encoders to learn not only view-wise discriminability but also cross-view complementary information.
  arXiv  Detail & Related papers  (2022-09-16T09:24:00Z)
• Technical Challenges for Training Fair Neural Networks [62.466658247995404]
  We conduct experiments on both facial recognition and automated medical diagnosis datasets using state-of-the-art architectures. We observe that large models overfit to fairness objectives, and produce a range of unintended and undesirable consequences.
  arXiv  Detail & Related papers  (2021-02-12T20:36:45Z)

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.