Langevin Unlearning: A New Perspective of Noisy Gradient Descent for
Machine Unlearning
- URL: http://arxiv.org/abs/2401.10371v4
- Date: Wed, 7 Feb 2024 19:08:28 GMT
- Title: Langevin Unlearning: A New Perspective of Noisy Gradient Descent for
Machine Unlearning
- Authors: Eli Chien, Haoyu Wang, Ziang Chen, Pan Li
- Abstract summary: Privacy is defined as statistical inperturbability to retraining from scratch.
We propose Langevin unlearning, an unlearning framework based on gradient descent.
- Score: 22.44567318992487
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Machine unlearning has raised significant interest with the adoption of laws
ensuring the ``right to be forgotten''. Researchers have provided a
probabilistic notion of approximate unlearning under a similar definition of
Differential Privacy (DP), where privacy is defined as statistical
indistinguishability to retraining from scratch. We propose Langevin
unlearning, an unlearning framework based on noisy gradient descent with
privacy guarantees for approximate unlearning problems. Langevin unlearning
unifies the DP learning process and the privacy-certified unlearning process
with many algorithmic benefits. These include approximate certified unlearning
for non-convex problems, complexity saving compared to retraining, sequential
and batch unlearning for multiple unlearning requests. We verify the
practicality of Langevin unlearning by studying its privacy-utility-complexity
trade-off via experiments on benchmark datasets, and also demonstrate its
superiority against gradient-decent-plus-output-perturbation based approximate
unlearning.
Related papers
- Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models [79.28821338925947]
Domain-Class Incremental Learning is a realistic but challenging continual learning scenario.
To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability.
This incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability.
Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy overhead.
We propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of
arXiv Detail & Related papers (2024-07-07T12:19:37Z) - Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios [18.73206066109299]
Mini-Unlearning is a novel approach that capitalizes on a critical observation: unlearned parameters correlate with retrained parameters through contraction mapping.
This lightweight, scalable method significantly enhances model accuracy and strengthens resistance to membership inference attacks.
Our experiments demonstrate that Mini-Unlearning not only works under higher unlearning ratios but also outperforms existing techniques in both accuracy and security.
arXiv Detail & Related papers (2024-06-24T01:43:30Z) - Stochastic Gradient Langevin Unlearning [20.546589699647416]
This work proposes Langevin unlearning, the first unlearning framework based on noisy gradient descent.
Our results show that mini-batch gradient updates provide a superior privacy-complexity trade-off compared to the full-batch counterpart.
arXiv Detail & Related papers (2024-03-25T18:43:58Z) - Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer
Level Attack and Knowledge Distillation [21.587358050012032]
We propose a fast and novel machine unlearning paradigm at the layer level called layer attack unlearning.
In this work, we introduce the Partial-PGD algorithm to locate the samples to forget efficiently.
We also use Knowledge Distillation (KD) to reliably learn the decision boundaries from the teacher.
arXiv Detail & Related papers (2023-12-28T04:38:06Z) - Locally Differentially Private Gradient Tracking for Distributed Online
Learning over Directed Graphs [2.1271873498506038]
We propose a locally differentially private gradient tracking based distributed online learning algorithm.
We prove that the proposed algorithm converges in mean square to the exact optimal solution while ensuring rigorous local differential privacy.
arXiv Detail & Related papers (2023-10-24T18:15:25Z) - Resilient Constrained Learning [94.27081585149836]
This paper presents a constrained learning approach that adapts the requirements while simultaneously solving the learning task.
We call this approach resilient constrained learning after the term used to describe ecological systems that adapt to disruptions by modifying their operation.
arXiv Detail & Related papers (2023-06-04T18:14:18Z) - When Do Curricula Work in Federated Learning? [56.88941905240137]
We find that curriculum learning largely alleviates non-IIDness.
The more disparate the data distributions across clients the more they benefit from learning.
We propose a novel client selection technique that benefits from the real-world disparity in the clients.
arXiv Detail & Related papers (2022-12-24T11:02:35Z) - Near-optimal Offline Reinforcement Learning with Linear Representation:
Leveraging Variance Information with Pessimism [65.46524775457928]
offline reinforcement learning seeks to utilize offline/historical data to optimize sequential decision-making strategies.
We study the statistical limits of offline reinforcement learning with linear model representations.
arXiv Detail & Related papers (2022-03-11T09:00:12Z) - Vertical Machine Unlearning: Selectively Removing Sensitive Information
From Latent Feature Space [21.8933559159369]
We investigate a vertical unlearning mode, aiming at removing only sensitive information from latent feature space.
We introduce intuitive and formal definitions for this unlearning and show its relationship with existing horizontal unlearning.
We propose an approximation with an upper bound to estimate it, with rigorous theoretical analysis.
arXiv Detail & Related papers (2022-02-27T05:25:15Z) - Simple Stochastic and Online Gradient DescentAlgorithms for Pairwise
Learning [65.54757265434465]
Pairwise learning refers to learning tasks where the loss function depends on a pair instances.
Online descent (OGD) is a popular approach to handle streaming data in pairwise learning.
In this paper, we propose simple and online descent to methods for pairwise learning.
arXiv Detail & Related papers (2021-11-23T18:10:48Z) - On Covariate Shift of Latent Confounders in Imitation and Reinforcement
Learning [69.48387059607387]
We consider the problem of using expert data with unobserved confounders for imitation and reinforcement learning.
We analyze the limitations of learning from confounded expert data with and without external reward.
We validate our claims empirically on challenging assistive healthcare and recommender system simulation tasks.
arXiv Detail & Related papers (2021-10-13T07:31:31Z)
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.