Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting
By: Sai Siddhartha Chary Aylapuram, Veeraraju Elluru, Shivang Agarwal
Potential Business Impact:
Fixes computer "seeing" to be fair.
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.
Similar Papers
Fairness and Robustness in Machine Unlearning
Machine Learning (CS)
Makes AI forget private data without losing skill.
Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
Cryptography and Security
Makes AI forget bad things without breaking good things.
Enabling Group Fairness in Graph Unlearning via Bi-level Debiasing
Machine Learning (CS)
Makes AI fairer when removing private data.