Adaptive Machine Unlearning

• URL: http://arxiv.org/abs/2106.04378v1
• Date: Tue, 8 Jun 2021 14:11:53 GMT
• Title: Adaptive Machine Unlearning
• Authors: Varun Gupta, Christopher Jung, Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi, Chris Waites
• Abstract summary: SIS flexible retraining aim to remove deleted data points from models at a cheaper computational retraining than fully trained models. We show how prior work gives guarantees for non-adaptive deletion sequences, giving strong provable deletion guarantees for extremely strong algorithms.
• Score: 21.294828533009838
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data deletion algorithms aim to remove the influence of deleted data points from trained models at a cheaper computational cost than fully retraining those models. However, for sequences of deletions, most prior work in the non-convex setting gives valid guarantees only for sequences that are chosen independently of the models that are published. If people choose to delete their data as a function of the published models (because they don't like what the models reveal about them, for example), then the update sequence is adaptive. In this paper, we give a general reduction from deletion guarantees against adaptive sequences to deletion guarantees against non-adaptive sequences, using differential privacy and its connection to max information. Combined with ideas from prior work which give guarantees for non-adaptive deletion sequences, this leads to extremely flexible algorithms able to handle arbitrary model classes and training methodologies, giving strong provable deletion guarantees for adaptive deletion sequences. We show in theory how prior work for non-convex models fails against adaptive deletion sequences, and use this intuition to design a practical attack against the SISA algorithm of Bourtoule et al. [2021] on CIFAR-10, MNIST, Fashion-MNIST.

Related papers

• ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning [51.133569963553576]
  ssToken is a Self-modulated and Semantic-aware Token Selection approach.<n>We show that both self-modulated selection and semantic-aware selection alone outperform full-data fine-tuning.
  arXiv  Detail & Related papers  (2025-10-21T03:21:04Z)
• Adaptive Off-Policy Inference for M-Estimators Under Model Misspecification [32.7750904494144]
  We propose a method that provides valid inference for M-estimators that use adaptively collected bandit data.<n>A key ingredient in our approach is the use of flexible machine learning approaches to stabilize the variance induced by adaptive data collection.
  arXiv  Detail & Related papers  (2025-09-17T17:51:40Z)
• UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning [57.081646768835704]
  User specifications or legal frameworks often require information to be removed from pretrained models, including large language models (LLMs) This requires deleting or "forgetting" a set of data points from an already-trained model, which typically degrades its performance on other data points. We propose UPCORE, a method-agnostic data selection framework for mitigating collateral damage during unlearning.
  arXiv  Detail & Related papers  (2025-02-20T22:51:10Z)
• Efficient and Generalizable Certified Unlearning: A Hessian-free Recollection Approach [8.875278412741695]
  Machine unlearning strives to uphold the data owners' right to be forgotten by enabling models to selectively forget specific data. We develop an algorithm that achieves near-instantaneous unlearning as it only requires a vector addition operation.
  arXiv  Detail & Related papers  (2024-04-02T07:54:18Z)
• Adaptive Optimization for Prediction with Missing Data [6.800113478497425]
  We show that some adaptive linear regression models are equivalent to learning an imputation rule and a downstream linear regression model simultaneously. In settings where data is strongly not missing at random, our methods achieve a 2-10% improvement in out-of-sample accuracy.
  arXiv  Detail & Related papers  (2024-02-02T16:35:51Z)
• Erasing Undesirable Influence in Diffusion Models [51.225365010401006]
  Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content. In this work, we introduce EraseDiff, an algorithm designed to preserve the utility of the diffusion model on retained data while removing the unwanted information associated with the data to be forgotten.
  arXiv  Detail & Related papers  (2024-01-11T09:30:36Z)
• Stable Training of Probabilistic Models Using the Leave-One-Out Maximum Log-Likelihood Objective [0.7373617024876725]
  Kernel density estimation (KDE) based models are popular choices for this task, but they fail to adapt to data regions with varying densities. An adaptive KDE model is employed to circumvent this, where each kernel in the model has an individual bandwidth. A modified expectation-maximization algorithm is employed to accelerate the optimization speed reliably.
  arXiv  Detail & Related papers  (2023-10-05T14:08:42Z)
• SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking [60.109453252858806]
  A maximum-likelihood (MLE) objective does not match a downstream use-case of autoregressively generating high-quality sequences. We formulate sequence generation as an imitation learning (IL) problem. This allows us to minimize a variety of divergences between the distribution of sequences generated by an autoregressive model and sequences from a dataset. Our resulting method, SequenceMatch, can be implemented without adversarial training or architectural changes.
  arXiv  Detail & Related papers  (2023-06-08T17:59:58Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)
• Online Forgetting Process for Linear Regression Models [18.336825781223034]
  Motivated by the EU's "Right To Be Forgotten" regulation, we initiate a study of statistical data deletion problems. We propose a deletion-aware algorithm textttFIFD-OLS for the low dimensional case, and witness a catastrophic rank swinging phenomenon. As a remedy, we propose the textttFIFD-Adaptive Ridge algorithm with a novel online regularization scheme.
  arXiv  Detail & Related papers  (2020-12-03T02:57:53Z)
• Autoregressive Score Matching [113.4502004812927]
  We propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariable log-conditionals (scores) For AR-CSM models, this divergence between data and model distributions can be computed and optimized efficiently, requiring no expensive sampling or adversarial training. We show with extensive experimental results that it can be applied to density estimation on synthetic data, image generation, image denoising, and training latent variable models with implicit encoders.
  arXiv  Detail & Related papers  (2020-10-24T07:01:24Z)
• Compressive Summarization with Plausibility and Salience Modeling [54.37665950633147]
  We propose to relax the rigid syntactic constraints on candidate spans and instead leave compression decisions to two data-driven criteria: plausibility and salience. Our method achieves strong in-domain results on benchmark summarization datasets, and human evaluation shows that the plausibility model generally selects for grammatical and factual deletions.
  arXiv  Detail & Related papers  (2020-10-15T17:07:10Z)
• Descent-to-Delete: Gradient-Based Methods for Machine Unlearning [15.647473776016042]
  We give the first data deletion algorithms that are able to handle an arbitrarily long sequence of adversarial updates. We introduce several new conceptual distinctions: for example, we can ask that after a deletion, the entire state maintained by the optimization algorithm is statistically indistinguishable from the state that would have resulted had we retrained.
  arXiv  Detail & Related papers  (2020-07-06T17:54:35Z)
• Slice Sampling for General Completely Random Measures [74.24975039689893]
  We present a novel Markov chain Monte Carlo algorithm for posterior inference that adaptively sets the truncation level using auxiliary slice variables. The efficacy of the proposed algorithm is evaluated on several popular nonparametric models.
  arXiv  Detail & Related papers  (2020-06-24T17:53:53Z)

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.