Evaluating Inexact Unlearning Requires Revisiting Forgetting

• URL: http://arxiv.org/abs/2201.06640v1
• Date: Mon, 17 Jan 2022 21:49:21 GMT
• Title: Evaluating Inexact Unlearning Requires Revisiting Forgetting
• Authors: Shashwat Goel, Ameya Prabhu and Ponnurangam Kumaraguru
• Abstract summary: We introduce a novel test to measure the degree of forgetting called Interclass Confusion (IC) Despite being a black-box test, IC can investigate whether information from the deletion set was erased until the early layers of the network. We empirically show that two simple unlearning methods, exact-unlearning and catastrophic-forgetting the final k layers of a network, scale well to large deletion sets unlike prior unlearning methods.
• Score: 14.199668091405064
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing works in inexact machine unlearning focus on achieving indistinguishability from models retrained after removing the deletion set. We argue that indistinguishability is unnecessary, infeasible to measure, and its practical relaxations can be insufficient. We redefine the goal of unlearning as forgetting all information specific to the deletion set while maintaining high utility and resource efficiency. Motivated by the practical application of removing mislabelled and biased data from models, we introduce a novel test to measure the degree of forgetting called Interclass Confusion (IC). It allows us to analyze two aspects of forgetting: (i) memorization and (ii) property generalization. Despite being a black-box test, IC can investigate whether information from the deletion set was erased until the early layers of the network. We empirically show that two simple unlearning methods, exact-unlearning and catastrophic-forgetting the final k layers of a network, scale well to large deletion sets unlike prior unlearning methods. k controls the forgetting-efficiency tradeoff at similar utility. Overall, we believe our formulation of unlearning and the IC test will guide the design of better unlearning algorithms.

Related papers

• RESTOR: Knowledge Recovery through Machine Unlearning [71.75834077528305]
  Large language models trained on web-scale corpora can memorize undesirable datapoints. Many machine unlearning methods have been proposed that aim to 'erase' these datapoints from trained models. We propose the RESTOR framework for machine unlearning based on the following dimensions.
  arXiv  Detail & Related papers  (2024-10-31T20:54:35Z)
• A Closer Look at Machine Unlearning for Large Language Models [46.245404272612795]
  Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. We discuss several issues in machine unlearning for LLMs and provide our insights on possible approaches.
  arXiv  Detail & Related papers  (2024-10-10T16:56:05Z)
• Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions [11.955062839855334]
  Machine unlearning algorithms aim to efficiently data from a model without it from scratch, in order to enforce data privacy, remove corrupted or outdated data, or respect a user's right to forgotten" Our algorithm is black-box, in that it be directly applied to models with vanilla gradient descent with no prior consideration of unlearning.
  arXiv  Detail & Related papers  (2024-09-15T15:58:08Z)
• A More Practical Approach to Machine Unlearning [0.0]
  Machine unlearning is the ability to remove the influence of specific data points from a trained model. The embedding layer in GPT-2 is crucial for effective unlearning. Fuzzy matching techniques shift the model to a new optimum, while iterative unlearning provides a more complete modality.
  arXiv  Detail & Related papers  (2024-06-13T17:59:06Z)
• Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning [97.2995389188179]
  Recent research has begun to approach large language models (LLMs) unlearning via gradient ascent (GA) Despite their simplicity and efficiency, we suggest that GA-based methods face the propensity towards excessive unlearning. We propose several controlling methods that can regulate the extent of excessive unlearning.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Decoupling the Class Label and the Target Concept in Machine Unlearning [81.69857244976123]
  Machine unlearning aims to adjust a trained model to approximate a retrained one that excludes a portion of training data. Previous studies showed that class-wise unlearning is successful in forgetting the knowledge of a target class. We propose a general framework, namely, TARget-aware Forgetting (TARF)
  arXiv  Detail & Related papers  (2024-06-12T14:53:30Z)
• Adaptive Rentention & Correction for Continual Learning [114.5656325514408]
  A common problem in continual learning is the classification layer's bias towards the most recent task. We name our approach Adaptive Retention & Correction (ARC) ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
  arXiv  Detail & Related papers  (2024-05-23T08:43:09Z)
• EvCenterNet: Uncertainty Estimation for Object Detection using Evidential Learning [26.535329379980094]
  EvCenterNet is a novel uncertainty-aware 2D object detection framework. We employ evidential learning to estimate both classification and regression uncertainties. We train our model on the KITTI dataset and evaluate it on challenging out-of-distribution datasets.
  arXiv  Detail & Related papers  (2023-03-06T11:07:11Z)
• Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers [71.70205894168039]
  We consider instance-wise unlearning, of which the goal is to delete information on a set of instances from a pre-trained model. We propose two methods that reduce forgetting on the remaining data: 1) utilizing adversarial examples to overcome forgetting at the representation-level and 2) leveraging weight importance metrics to pinpoint network parameters guilty of propagating unwanted information.
  arXiv  Detail & Related papers  (2023-01-27T07:53:50Z)
• On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning [13.149070833843133]
  Machine unlearning, i.e. having a model forget about some of its training data, has become increasingly important as privacy legislation promotes variants of the right-to-be-forgotten. We first show that the definition that underlies approximate unlearning, which seeks to prove the approximately unlearned model is close to an exactly retrained model, is incorrect because one can obtain the same model using different datasets. We then turn to exact unlearning approaches and ask how to verify their claims of unlearning.
  arXiv  Detail & Related papers  (2021-10-22T16:16:56Z)
• Machine Unlearning of Features and Labels [72.81914952849334]
  We propose first scenarios for unlearning and labels in machine learning models. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters.
  arXiv  Detail & Related papers  (2021-08-26T04:42:24Z)

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.