Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspective

• URL: http://arxiv.org/abs/2410.03833v2
• Date: Fri, 07 Feb 2025 22:08:38 GMT
• Title: Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspective
• Authors: Meng Ding, Rohan Sharma, Changyou Chen, Jinhui Xu, Kaiyi Ji,
• Abstract summary: Fine-tuning (FT) methods have become one of the fundamental approaches for approximating unlearning. We present the first theoretical analysis of FT methods for machine unlearning within a linear regression framework. We propose a novel Retention-Based Masking (RBM) strategy that constructs a weight saliency map based on the remaining dataset.
• Score: 39.958103832214135
• License:
• Abstract: Machine Unlearning has emerged as a significant area of research, focusing on `removing' specific subsets of data from a trained model. Fine-tuning (FT) methods have become one of the fundamental approaches for approximating unlearning, as they effectively retain model performance. However, it is consistently observed that naive FT methods struggle to forget the targeted data. In this paper, we present the first theoretical analysis of FT methods for machine unlearning within a linear regression framework, providing a deeper exploration of this phenomenon. Our analysis reveals that while FT models can achieve zero remaining loss, they fail to forget the forgetting data, as the pretrained model retains its influence and the fine-tuning process does not adequately mitigate it. To address this, we propose a novel Retention-Based Masking (RBM) strategy that constructs a weight saliency map based on the remaining dataset, unlike existing methods that focus on the forgetting dataset. Our theoretical analysis demonstrates that RBM not only significantly improves unlearning accuracy (UA) but also ensures higher retaining accuracy (RA) by preserving overlapping features shared between the forgetting and remaining datasets. Experiments on synthetic and real-world datasets validate our theoretical insights, showing that RBM outperforms existing masking approaches in balancing UA, RA, and disparity metrics.

Related papers

• Physics-Driven Self-Supervised Deep Learning for Free-Surface Multiple Elimination [3.3244277562036095]
  In geophysics, deep learning (DL) methods are commonly based on supervised learning from large amounts of high-quality labelled data. We propose a method in which the DL model learns to effectively parameterize the free-surface multiple-free wavefield from the full wavefield by incorporating the underlying physics into the loss computation. This, in turn, yields high-quality estimates without ever being shown any ground truth data.
  arXiv  Detail & Related papers  (2025-01-26T15:37:23Z)
• Distribution Learning for Molecular Regression [10.96062816455682]
  Distributional Mixture of Experts (DMoE) is a model-independent, and data-independent method for regression. We evaluate the performance of DMoE on different molecular property prediction datasets.
  arXiv  Detail & Related papers  (2024-07-30T00:21:51Z)
• Extracting Training Data from Unconditional Diffusion Models [76.85077961718875]
  diffusion probabilistic models (DPMs) are being employed as mainstream models for generative artificial intelligence (AI) We aim to establish a theoretical understanding of memorization in DPMs with 1) a memorization metric for theoretical analysis, 2) an analysis of conditional memorization with informative and random labels, and 3) two better evaluation metrics for measuring memorization. Based on the theoretical analysis, we propose a novel data extraction method called textbfSurrogate condItional Data Extraction (SIDE) that leverages a trained on generated data as a surrogate condition to extract training data directly from unconditional diffusion models.
  arXiv  Detail & Related papers  (2024-06-18T16:20:12Z)
• Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning [28.059563581973432]
  Large Language Models (LLMs) often have sensitive, private, or copyrighted data during pre-training. LLMs unlearning aims to eliminate the influence of undesirable data from the pre-trained model. We propose Negative Preference Optimization (NPO) as a simple alignment-inspired method that could efficiently unlearn a target dataset.
  arXiv  Detail & Related papers  (2024-04-08T21:05:42Z)
• AST: Effective Dataset Distillation through Alignment with Smooth and High-Quality Expert Trajectories [18.266786462036553]
  We propose an effective DD framework named AST, standing for Alignment with Smooth and high-quality expert Trajectories. We conduct extensive experiments on datasets of different scales, sizes, and resolutions.
  arXiv  Detail & Related papers  (2023-10-16T16:13:53Z)
• Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation [151.70234052015948]
  We propose a novel approach that encourages the optimization algorithm to seek a flat trajectory. We show that the weights trained on synthetic data are robust against the accumulated errors perturbations with the regularization towards the flat trajectory. Our method, called Flat Trajectory Distillation (FTD), is shown to boost the performance of gradient-matching methods by up to 4.7%.
  arXiv  Detail & Related papers  (2022-11-20T15:49:11Z)
• Bias-inducing geometries: an exactly solvable data model with fairness implications [12.532003449620607]
  We introduce an exactly solvable high-dimensional model of data imbalance. We analytically unpack the typical properties of learning models trained in this synthetic framework. We obtain exact predictions for the observables that are commonly employed for fairness assessment.
  arXiv  Detail & Related papers  (2022-05-31T16:27:57Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Imputation-Free Learning from Incomplete Observations [73.15386629370111]
  We introduce the importance of guided gradient descent (IGSGD) method to train inference from inputs containing missing values without imputation. We employ reinforcement learning (RL) to adjust the gradients used to train the models via back-propagation. Our imputation-free predictions outperform the traditional two-step imputation-based predictions using state-of-the-art imputation methods.
  arXiv  Detail & Related papers  (2021-07-05T12:44:39Z)
• Graph Embedding with Data Uncertainty [113.39838145450007]
  spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines. Most subspace learning methods do not take into consideration possible measurement inaccuracies or artifacts that can lead to data with high uncertainty.
  arXiv  Detail & Related papers  (2020-09-01T15:08:23Z)

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.