Provable Fairness Repair for Deep Neural Networks

• URL: http://arxiv.org/abs/2605.19549v1
• Date: Tue, 19 May 2026 08:46:55 GMT
• Title: Provable Fairness Repair for Deep Neural Networks
• Abstract summary: Deep neural networks (DNNs) are suffering from ethical issues such as individual discrimination.<n>We propose ProF, a novel fairness repair framework with provable guarantees.<n>We demonstrate that ProF achieves provable fairness repair, with generalization of up to 95.93% on full datasets and 93.16% on the entire input space.
• Score: 11.183772232721068
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks (DNNs) are suffering from ethical issues such as individual discrimination. In response, extensive NN repair techniques have been developed to adjust models and mitigate such undesired behaviors. However, existing fairness repair methods are typically data-centric, which often lack provable guarantees and generalization to unseen samples. To overcome these limitations, we propose ProF, a novel fairness repair framework with provable guarantees. The key intuition of ProF is to leverage interval bound propagation (a widely used NN verification technique) to soundly capture model outputs over the whole set $S(\mathbf{x})$ around a biased sample $\mathbf{x}$. The derived bounds are utilized to guide fairness repair which encourages the model to produce consistent outputs on $S(\mathbf{x})$. Specifically, we integrate fairness constraints and model modifications into a unified constraint-solving formulation, which can be transformed to a Mixed-Integer Linear Programming (MILP) problem solvable by off-the-shelf solvers. The solution to the MILP problem effectively induces a repaired model with guaranteed fairness over the whole set $S(\mathbf{x})$. We evaluate ProF on four widely used benchmark datasets and demonstrate that it achieves provable fairness repair, with generalization of up to 95.93\% on full datasets and 93.16\% on the entire input space. Notably, ProF can be easily configured to support multiple sensitive attributes and more practical fairness definitions, while providing provable repair guarantees and delivering around 90\% fairness improvement. Our code is available at https://github.com/nninjn/ProF.

Related papers

• Reinforcement Learning from Multi-Source Imperfect Preferences: Best-of-Both-Regimes Regret [71.69884486156359]
  We study episodic RL from emphmulti-source imperfect preferences through a cumulative imperfection budget.<n>We propose a unified algorithm with regret $tildeO(sqrtK/M+)$, which exhibits a best-of-both-regimes behavior.
  arXiv  Detail & Related papers  (2026-03-20T19:34:53Z)
• Fair Bayesian Data Selection via Generalized Discrepancy Measures [11.013077130984973]
  We propose a data selection framework that ensures fairness by aligning group-specific posterior distributions of model parameters and sample weights with a shared central distribution.<n>Our framework supports flexible alignment via various distributional discrepancy measures, including Wasserstein distance, maximum mean discrepancy, and $f$-divergence.<n> Experiments on benchmark datasets show that our method consistently outperforms existing data selection and model-based fairness methods in both fairness and accuracy.
  arXiv  Detail & Related papers  (2025-11-10T12:28:04Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on Large Language Models [53.36415620647177]
  Semi-structured sparsity offers a promising solution by strategically retaining $N$ elements out of every $M$ weights.<n>Existing (N:M)-compatible approaches typically fall into two categories: rule-based layerwise greedy search, which suffers from considerable errors, and gradient-driven learning, which incurs prohibitive training costs.<n>We propose a novel linear-space probabilistic framework named MaskPro, which aims to learn a prior categorical distribution for every $M$ consecutive weights and subsequently leverages this distribution to generate the (N:M)-sparsity throughout an $N$-way sampling
  arXiv  Detail & Related papers  (2025-06-15T15:02:59Z)
• Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs [71.7892165868749]
  Commercial Large Language Model (LLM) APIs create a fundamental trust problem.<n>Users pay for specific models but have no guarantee that providers deliver them faithfully.<n>We formalize this model substitution problem and evaluate detection methods under realistic adversarial conditions.<n>We propose and evaluate the use of Trusted Execution Environments (TEEs) as one practical and robust solution.
  arXiv  Detail & Related papers  (2025-04-07T03:57:41Z)
• 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)
• Fair CoVariance Neural Networks [34.68621550644667]
  We propose Fair coVariance Neural Networks (FVNNs), which perform graph convolutions on the covariance matrix for both fair and accurate predictions.<n>We prove that FVNNs are intrinsically fairer than analogous PCA approaches thanks to their stability in low sample regimes.
  arXiv  Detail & Related papers  (2024-09-13T06:24:18Z)
• Achievable Fairness on Your Data With Utility Guarantees [16.78730663293352]
  In machine learning fairness, training models that minimize disparity across different sensitive groups often leads to diminished accuracy. We present a computationally efficient approach to approximate the fairness-accuracy trade-off curve tailored to individual datasets. We introduce a novel methodology for quantifying uncertainty in our estimates, thereby providing practitioners with a robust framework for auditing model fairness.
  arXiv  Detail & Related papers  (2024-02-27T00:59:32Z)
• An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning [55.467047686093025]
  A common approach to alleviate such forgetting is to rehearse samples from prior tasks during fine-tuning.<n>We propose a sampling scheme, textttbf mix-cd, that prioritizes rehearsal of collateral damage'' samples.<n>Our approach is computationally efficient, easy to implement, and outperforms several leading continual learning methods in compute-constrained settings.
  arXiv  Detail & Related papers  (2024-02-12T22:32:12Z)
• Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach [72.19525160912943]
  We first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and model weight perturbation. We then analyze the sufficient conditions to guarantee fairness for the target dataset. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR)
  arXiv  Detail & Related papers  (2023-03-06T17:19:23Z)
• Individual Fairness Guarantees for Neural Networks [0.0]
  We consider the problem of certifying the individual fairness (IF) of feed-forward neural networks (NNs) We work with the $epsilon$-$delta$-IF formulation, which requires that the output difference between any pair of $epsilon$-similar individuals is bounded by a maximum decision tolerance. We show how this formulation can be used to encourage models' fairness at training time by modifying the NN loss, and empirically confirm our approach yields NNs that are orders of magnitude fairer than state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-05-11T20:21:07Z)

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.