Targeted Unlearning Using Perturbed Sign Gradient Methods With Applications On Medical Images

TL;DR

This paper presents a bilevel optimization-based method for machine unlearning in medical imaging, enabling efficient model updates post-deployment with guarantees and improved performance over existing approaches.

Contribution

It introduces a novel boundary-based unlearning framework with convergence guarantees, tunable tradeoffs, and model composition strategies for clinical applications.

Findings

Outperforms baselines on forgetting and retention metrics

Effective in clinical imaging datasets with device and anatomical variations

Supports practical, modular model maintenance in healthcare

Abstract

Machine unlearning aims to remove the influence of specific training samples from a trained model without full retraining. While prior work has largely focused on privacy-motivated settings, we recast unlearning as a general-purpose tool for post-deployment model revision. Specifically, we focus on utilizing unlearning in clinical contexts where data shifts, device deprecation, and policy changes are common. To this end, we propose a bilevel optimization formulation of boundary-based unlearning that can be solved using iterative algorithms. We provide convergence guarantees when first-order algorithms are used to unlearn. Our method introduces tunable loss design for controlling the forgetting-retention tradeoff and supports novel model composition strategies that merge the strengths of distinct unlearning runs. Across benchmark and real-world clinical imaging datasets, our approach outperforms baselines on both forgetting and retention metrics, including scenarios involving imaging devices and anatomical outliers. This work establishes machine unlearning as a modular, practical alternative to retraining for real-world model maintenance in clinical applications.