Unlearning Traces the Influential Training Data of Language Models

• URL: http://arxiv.org/abs/2401.15241v2
• Date: Thu, 13 Jun 2024 16:28:47 GMT
• Title: Unlearning Traces the Influential Training Data of Language Models
• Authors: Masaru Isonuma, Ivan Titov,
• Abstract summary: This paper presents UnTrac: unlearning traces the influence of a training dataset on the model's performance. We propose a more scalable approach, UnTrac-Inv, which unlearns a test dataset and evaluates the unlearned model on training datasets.
• Score: 31.33791825286853
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Identifying the training datasets that influence a language model's outputs is essential for minimizing the generation of harmful content and enhancing its performance. Ideally, we can measure the influence of each dataset by removing it from training; however, it is prohibitively expensive to retrain a model multiple times. This paper presents UnTrac: unlearning traces the influence of a training dataset on the model's performance. UnTrac is extremely simple; each training dataset is unlearned by gradient ascent, and we evaluate how much the model's predictions change after unlearning. Furthermore, we propose a more scalable approach, UnTrac-Inv, which unlearns a test dataset and evaluates the unlearned model on training datasets. UnTrac-Inv resembles UnTrac, while being efficient for massive training datasets. In the experiments, we examine if our methods can assess the influence of pretraining datasets on generating toxic, biased, and untruthful content. Our methods estimate their influence much more accurately than existing methods while requiring neither excessive memory space nor multiple checkpoints.

Related papers

• Distilled Datamodel with Reverse Gradient Matching [74.75248610868685]
  We introduce an efficient framework for assessing data impact, comprising offline training and online evaluation stages. Our proposed method achieves comparable model behavior evaluation while significantly speeding up the process compared to the direct retraining method.
  arXiv  Detail & Related papers  (2024-04-22T09:16:14Z)
• Corrective Machine Unlearning [22.342035149807923]
  We formalize Corrective Machine Unlearning as the problem of mitigating the impact of data affected by unknown manipulations on a trained model. We find most existing unlearning methods, including retraining-from-scratch without the deletion set, require most of the manipulated data to be identified for effective corrective unlearning. One approach, Selective Synaptic Dampening, achieves limited success, unlearning adverse effects with just a small portion of the manipulated samples in our setting.
  arXiv  Detail & Related papers  (2024-02-21T18:54:37Z)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks [91.15120211190519]
  This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. We propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise.
  arXiv  Detail & Related papers  (2023-09-29T06:18:15Z)
• TRAK: Attributing Model Behavior at Scale [79.56020040993947]
  We present TRAK (Tracing with Randomly-trained After Kernel), a data attribution method that is both effective and computationally tractable for large-scale, differenti models.
  arXiv  Detail & Related papers  (2023-03-24T17:56:22Z)
• 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)
• Certifiable Machine Unlearning for Linear Models [1.484852576248587]
  Machine unlearning is the task of updating machine learning (ML) models after a subset of the training data they were trained on is deleted. We present an experimental study of the three state-of-the-art approximate unlearning methods for linear models.
  arXiv  Detail & Related papers  (2021-06-29T05:05:58Z)
• Coded Machine Unlearning [34.08435990347253]
  We present a coded learning protocol where the dataset is linearly coded before the learning phase. We also present the corresponding unlearning protocol for the coded learning model along with a discussion on the proposed protocol's success in ensuring perfect unlearning.
  arXiv  Detail & Related papers  (2020-12-31T17:20:34Z)
• Efficient Estimation of Influence of a Training Instance [56.29080605123304]
  We propose an efficient method for estimating the influence of a training instance on a neural network model. Our method is inspired by dropout, which zero-masks a sub-network and prevents the sub-network from learning each training instance. We demonstrate that the proposed method can capture training influences, enhance the interpretability of error predictions, and cleanse the training dataset for improving generalization.
  arXiv  Detail & Related papers  (2020-12-08T04:31:38Z)

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.