An Introduction to Machine Unlearning
- URL: http://arxiv.org/abs/2209.00939v1
- Date: Fri, 2 Sep 2022 10:24:50 GMT
- Title: An Introduction to Machine Unlearning
- Authors: Salvatore Mercuri, Raad Khraishi, Ramin Okhrati, Devesh Batra, Conor
Hamill, Taha Ghasempour, Andrew Nowlan
- Abstract summary: We summarise and compare seven state-of-the-art machine unlearning algorithms.
We consolidate definitions of core concepts used in the field.
We discuss issues related to applying machine unlearning in practice.
- Score: 0.6649973446180738
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Removing the influence of a specified subset of training data from a machine
learning model may be required to address issues such as privacy, fairness, and
data quality. Retraining the model from scratch on the remaining data after
removal of the subset is an effective but often infeasible option, due to its
computational expense. The past few years have therefore seen several novel
approaches towards efficient removal, forming the field of "machine
unlearning", however, many aspects of the literature published thus far are
disparate and lack consensus. In this paper, we summarise and compare seven
state-of-the-art machine unlearning algorithms, consolidate definitions of core
concepts used in the field, reconcile different approaches for evaluating
algorithms, and discuss issues related to applying machine unlearning in
practice.
Related papers
- Adversarial Machine Unlearning [26.809123658470693]
This paper focuses on the challenge of machine unlearning, aiming to remove the influence of specific training data on machine learning models.
Traditionally, the development of unlearning algorithms runs parallel with that of membership inference attacks (MIA), a type of privacy threat.
We propose a game-theoretic framework that integrates MIAs into the design of unlearning algorithms.
arXiv Detail & Related papers (2024-06-11T20:07:22Z) - Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning [0.0]
We describe and propose alternative evaluation methods for machine unlearning algorithms.
We show the utility of our alternative evaluations via a series of experiments of state-of-the-art unlearning algorithms on different computer vision datasets.
arXiv Detail & Related papers (2024-05-29T15:53:23Z) - The Frontier of Data Erasure: Machine Unlearning for Large Language Models [56.26002631481726]
Large Language Models (LLMs) are foundational to AI advancements.
LLMs pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information.
Machine unlearning emerges as a cutting-edge solution to mitigate these concerns.
arXiv Detail & Related papers (2024-03-23T09:26:15Z) - Loss-Free Machine Unlearning [51.34904967046097]
We present a machine unlearning approach that is both retraining- and label-free.
Retraining-free approaches often utilise Fisher information, which is derived from the loss and requires labelled data which may not be available.
We present an extension to the Selective Synaptic Dampening algorithm, substituting the diagonal of the Fisher information matrix for the gradient of the l2 norm of the model output to approximate sensitivity.
arXiv Detail & Related papers (2024-02-29T16:15:34Z) - Dataset Condensation Driven Machine Unlearning [0.0]
Current trend in data regulation requirements and privacy-preserving machine learning has emphasized the importance of machine unlearning.
We propose new dataset condensation techniques and an innovative unlearning scheme that strikes a balance between machine unlearning privacy, utility, and efficiency.
We present a novel and effective approach to instrumenting machine unlearning and propose its application in defending against membership inference and model inversion attacks.
arXiv Detail & Related papers (2024-01-31T21:48:25Z) - DUCK: Distance-based Unlearning via Centroid Kinematics [40.2428948628001]
This work introduces a novel unlearning algorithm, denoted as Distance-based Unlearning via Centroid Kinematics (DUCK)
evaluation of the algorithm's performance is conducted across various benchmark datasets.
We also introduce a novel metric, called Adaptive Unlearning Score (AUS), encompassing not only the efficacy of the unlearning process in forgetting target data but also quantifying the performance loss relative to the original model.
arXiv Detail & Related papers (2023-12-04T17:10:25Z) - Advancing Reacting Flow Simulations with Data-Driven Models [50.9598607067535]
Key to effective use of machine learning tools in multi-physics problems is to couple them to physical and computer models.
The present chapter reviews some of the open opportunities for the application of data-driven reduced-order modeling of combustion systems.
arXiv Detail & Related papers (2022-09-05T16:48:34Z) - Evaluating Machine Unlearning via Epistemic Uncertainty [78.27542864367821]
This work presents an evaluation of Machine Unlearning algorithms based on uncertainty.
This is the first definition of a general evaluation of our best knowledge.
arXiv Detail & Related papers (2022-08-23T09:37:31Z) - MACE: An Efficient Model-Agnostic Framework for Counterfactual
Explanation [132.77005365032468]
We propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE)
In our MACE approach, we propose a novel RL-based method for finding good counterfactual examples and a gradient-less descent method for improving proximity.
Experiments on public datasets validate the effectiveness with better validity, sparsity and proximity.
arXiv Detail & Related papers (2022-05-31T04:57:06Z) - Beyond Trivial Counterfactual Explanations with Diverse Valuable
Explanations [64.85696493596821]
In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction.
We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss.
Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
arXiv Detail & Related papers (2021-03-18T12:57:34Z) - Model-agnostic interpretation by visualization of feature perturbations [0.0]
We propose a model-agnostic interpretation approach that uses visualization of feature perturbations induced by the particle swarm optimization algorithm.
We validate our approach both qualitatively and quantitatively on publicly available datasets.
arXiv Detail & Related papers (2021-01-26T00:53:29Z)
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.