Distributional Machine Unlearning via Selective Data Removal

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Allouah, Youssef, Guerraoui, Rachid, Koyejo, Sanmi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911374290976768
author Allouah, Youssef
Guerraoui, Rachid
Koyejo, Sanmi
author_facet Allouah, Youssef
Guerraoui, Rachid
Koyejo, Sanmi
contents Machine learning systems increasingly face requirements to remove entire domains of information--such as toxic language or biases--rather than individual user data. This task presents a dilemma: full removal of the unwanted domain data is computationally expensive, while random partial removal is statistically inefficient. We find that a domain's statistical influence is often concentrated in a small subset of its data samples, suggesting a path between ineffective partial removal and unnecessary complete removal. We formalize this as distributional unlearning: a framework to select a small subset that balances forgetting an unwanted distribution while preserving a desired one. Using Kullback-Leibler divergence constraints, we derive the exact removal-preservation Pareto frontier for Gaussian distributions and prove that models trained on the edited data achieve corresponding log-loss bounds. We propose a distance-based selection algorithm and show it is quadratically more sample-efficient than random removal in the challenging low-divergence regime. Experiments across synthetic, text, and image datasets (Jigsaw, CIFAR-10, SMS spam) show our method requires 15-82% less deletion than full removal for strong unlearning effects, e.g., halving initial forget set accuracy. Ultimately, by showing a small forget set often suffices, our framework lays the foundations for more scalable and rigorous subpopulation unlearning.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15112
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Distributional Machine Unlearning via Selective Data Removal
Allouah, Youssef
Guerraoui, Rachid
Koyejo, Sanmi
Machine Learning
Cryptography and Security
Machine learning systems increasingly face requirements to remove entire domains of information--such as toxic language or biases--rather than individual user data. This task presents a dilemma: full removal of the unwanted domain data is computationally expensive, while random partial removal is statistically inefficient. We find that a domain's statistical influence is often concentrated in a small subset of its data samples, suggesting a path between ineffective partial removal and unnecessary complete removal. We formalize this as distributional unlearning: a framework to select a small subset that balances forgetting an unwanted distribution while preserving a desired one. Using Kullback-Leibler divergence constraints, we derive the exact removal-preservation Pareto frontier for Gaussian distributions and prove that models trained on the edited data achieve corresponding log-loss bounds. We propose a distance-based selection algorithm and show it is quadratically more sample-efficient than random removal in the challenging low-divergence regime. Experiments across synthetic, text, and image datasets (Jigsaw, CIFAR-10, SMS spam) show our method requires 15-82% less deletion than full removal for strong unlearning effects, e.g., halving initial forget set accuracy. Ultimately, by showing a small forget set often suffices, our framework lays the foundations for more scalable and rigorous subpopulation unlearning.
title Distributional Machine Unlearning via Selective Data Removal
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2507.15112