Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting

• URL: http://arxiv.org/abs/2509.07456v1
• Date: Tue, 09 Sep 2025 07:25:51 GMT
• Title: Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting
• Authors: Sai Siddhartha Chary Aylapuram, Veeraraju Elluru, Shivang Agarwal,
• Abstract summary: Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving.<n>Recent advances in machine unlearning provide a promising alternative for post-hoc model correction.
• Score: 3.1959623025848405
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires retraining from scratch or redesigning data pipelines, recent advances in machine unlearning provide a promising alternative for post-hoc model correction. In this work, we investigate \textit{Bias-Aware Machine Unlearning}, a paradigm that selectively removes biased samples or feature representations to mitigate diverse forms of bias in vision models. Building on privacy-preserving unlearning techniques, we evaluate various strategies including Gradient Ascent, LoRA, and Teacher-Student distillation. Through empirical analysis on three benchmark datasets, CUB-200-2011 (pose bias), CIFAR-10 (synthetic patch bias), and CelebA (gender bias in smile detection), we demonstrate that post-hoc unlearning can substantially reduce subgroup disparities, with improvements in demographic parity of up to \textbf{94.86\%} on CUB-200, \textbf{30.28\%} on CIFAR-10, and \textbf{97.37\%} on CelebA. These gains are achieved with minimal accuracy loss and with methods scoring an average of 0.62 across the 3 settings on the joint evaluation of utility, fairness, quality, and privacy. Our findings establish machine unlearning as a practical framework for enhancing fairness in deployed vision systems without necessitating full retraining.

Related papers

• Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling [105.8570596633629]
  We rethink long-tailed dataset distillation by revisiting the limitations of trajectory-based methods.<n>We adopt the statistical alignment perspective to jointly model bias and restore fair supervision.<n>Our approach improves top-1 accuracy by 15.6% on CIFAR-100-LT and 11.8% on Tiny-ImageNet-LT.
  arXiv  Detail & Related papers  (2025-11-24T07:57:01Z)
• C2AL: Cohort-Contrastive Auxiliary Learning for Large-scale Recommendation Systems [7.548682352355034]
  We show how the attention mechanism can play a key role in factorization machines for shared embedding selection.<n>We propose to address this challenge by analyzing the substructures in the dataset and exposing those with strong distributional contrast through auxiliary learning.<n>This approach customizes the learning process of attention layers to preserve mutual information with minority cohorts while improving global performance.
  arXiv  Detail & Related papers  (2025-10-02T17:00:17Z)
• BOOST: Out-of-Distribution-Informed Adaptive Sampling for Bias Mitigation in Stylistic Convolutional Neural Networks [8.960561031294727]
  Bias in AI presents a significant challenge to painting classification, and is getting more serious as these systems become increasingly integrated into tasks like art curation and restoration.<n>We propose a novel OOD-informed model bias adaptive sampling method called BOOST.<n>We evaluate our proposed approach to the KaoKore and PACS datasets, focusing on the model's ability to reduce class-wise bias.
  arXiv  Detail & Related papers  (2025-07-08T22:18:36Z)
• Privacy-Preserved Automated Scoring using Federated Learning for Educational Research [1.2556373621040728]
  We propose a federated learning (FL) framework for automated scoring of educational assessments.<n>We benchmark our model against two state-of-the-art FL methods and a centralized learning baseline.<n>Results show that our model achieves the highest accuracy (94.5%) among FL approaches.
  arXiv  Detail & Related papers  (2025-03-12T19:06:25Z)
• ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition [52.537021302246664]
  Action recognition models often suffer from background bias (i.e., inferring actions based on background cues) and foreground bias (i.e., relying on subject appearance)<n>We propose ALBAR, a novel adversarial training method that mitigates foreground and background biases without requiring specialized knowledge of the bias attributes.<n>We evaluate our method on established background and foreground bias protocols, setting a new state-of-the-art and strongly improving combined debiasing performance by over 12% absolute on HMDB51.
  arXiv  Detail & Related papers  (2025-01-31T20:47:06Z)
• Neural Corrective Machine Unranking [3.2340528215722553]
  We formalise corrective unranking and propose a novel teacher-student framework, Corrective unRanking Distillation (CuRD)<n>CuRD facilitates forgetting by adjusting the (trained) neural IR model such that its output relevance scores of to-be-forgotten samples mimic those of low-ranking, non-retrievable samples.<n>Experiments with forget set sizes from 1 % and 20 % of the training dataset demonstrate that CuRD outperforms seven state-of-the-art baselines in terms of forgetting and correction.
  arXiv  Detail & Related papers  (2024-11-13T12:19:46Z)
• Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy [65.80757820884476]
  We expose a critical yet underexplored vulnerability in the deployment of unlearning systems. We present a threat model where an attacker can degrade model accuracy by submitting adversarial unlearning requests for data not present in the training set. We evaluate various verification mechanisms to detect the legitimacy of unlearning requests and reveal the challenges in verification.
  arXiv  Detail & Related papers  (2024-10-12T16:47:04Z)
• Fast Model Debias with Machine Unlearning [54.32026474971696]
  Deep neural networks might behave in a biased manner in many real-world scenarios. Existing debiasing methods suffer from high costs in bias labeling or model re-training. We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
  arXiv  Detail & Related papers  (2023-10-19T08:10:57Z)
• Federated Zero-Shot Learning for Visual Recognition [55.65879596326147]
  We propose a novel Federated Zero-Shot Learning FedZSL framework. FedZSL learns a central model from the decentralized data residing on edge devices. The effectiveness and robustness of FedZSL are demonstrated by extensive experiments conducted on three zero-shot benchmark datasets.
  arXiv  Detail & Related papers  (2022-09-05T14:49:34Z)
• D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias [57.87117733071416]
  We propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases. A user can detect the presence of bias against a group by identifying unfair causal relationships in the causal network. For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset.
  arXiv  Detail & Related papers  (2022-08-10T03:41:48Z)
• Distraction is All You Need for Fairness [0.0]
  We propose a strategy for training deep learning models called the Distraction module. This method can be theoretically proven effective in controlling bias from affecting the classification results. We demonstrate the potency of the proposed method by testing it on UCI Adult and Heritage Health datasets.
  arXiv  Detail & Related papers  (2022-03-15T01:46:55Z)
• FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes [51.02407217197623]
  We propose a two-stage training algorithm named FAIRIF. It minimizes the loss over the reweighted data set where the sample weights are computed. We show that FAIRIF yields models with better fairness-utility trade-offs against various types of bias.
  arXiv  Detail & Related papers  (2022-01-15T05:14:48Z)
• Fair Meta-Learning For Few-Shot Classification [7.672769260569742]
  A machine learning algorithm trained on biased data tends to make unfair predictions. We propose a novel fair fast-adapted few-shot meta-learning approach that efficiently mitigates biases during meta-train. We empirically demonstrate that our proposed approach efficiently mitigates biases on model output and generalizes both accuracy and fairness to unseen tasks.
  arXiv  Detail & Related papers  (2020-09-23T22:33:47Z)

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.