A mean teacher algorithm for unlearning of language models

• URL: http://arxiv.org/abs/2504.13388v1
• Date: Fri, 18 Apr 2025 00:34:19 GMT
• Title: A mean teacher algorithm for unlearning of language models
• Authors: Yegor Klochkov,
• Abstract summary: We show that the mean teacher algorithm can approximate a trajectory of a slow natural gradient descent.<n>While slow NGD can suffer from vanishing gradients, we introduce a new unlearning loss called "negative log-unlikelihood" (NLUL) that avoids this problem.
• Score: 5.384630221560811
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: One of the goals of language model unlearning is to reduce memorization of selected text instances while retaining the model's general abilities. Despite various proposed methods, reducing memorization of large datasets without noticeable degradation in model utility remains challenging. In this paper, we investigate the mean teacher algorithm (Tarvainen & Valpola, 2017), a simple proximal optimization method from continual learning literature that gradually modifies the teacher model. We show that the mean teacher can approximate a trajectory of a slow natural gradient descent (NGD), which inherently seeks low-curvature updates that are less likely to degrade the model utility. While slow NGD can suffer from vanishing gradients, we introduce a new unlearning loss called "negative log-unlikelihood" (NLUL) that avoids this problem. We show that the combination of mean teacher and NLUL improves some metrics on the MUSE benchmarks (Shi et al., 2024).

Related papers

• Can Gradient Descent Simulate Prompting? [56.60154660021178]
  gradient updates the effects of conditioning on new information.<n> gradient descent training recovers some (and occasionally all) of prompted model performance.<n>Results suggest new avenues for long-context modeling.
  arXiv  Detail & Related papers  (2025-06-26T04:06:20Z)
• Multi-Objective Large Language Model Unlearning [3.372396620898397]
  Gradient Ascent (GA) is a proactive way to decrease the prediction probability of the model on the target data.<n>We propose Multi-Objective Large Language Model Unlearning (MOLLM) algorithm to overcome gradient explosion and catastrophic forgetting.<n>Our empirical results verify that MoLLM outperforms the SOTA GA-based LLM unlearning methods in terms of unlearning effect and model utility preservation.
  arXiv  Detail & Related papers  (2024-12-29T09:35:56Z)
• An Effective Dynamic Gradient Calibration Method for Continual Learning [11.555822066922508]
  Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks. Due to the memory limit, we cannot store all the historical data, and therefore confront the catastrophic forgetting'' problem. We develop an effective algorithm to calibrate the gradient in each updating step of the model.
  arXiv  Detail & Related papers  (2024-07-30T16:30:09Z)
• Targeted Unlearning with Single Layer Unlearning Gradient [15.374381635334897]
  Machine unlearning methods aim to remove sensitive or unwanted content from trained models.<n>We propose Single Layer Unlearning Gradient computation (SLUG) as an efficient method to unlearn targeted information.
  arXiv  Detail & Related papers  (2024-07-16T15:52:36Z)
• 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)
• BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping [64.54271680071373]
  Diffusion models have demonstrated excellent potential for generating diverse images. Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few. We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
  arXiv  Detail & Related papers  (2023-06-08T20:30:55Z)
• Meta-Learning Online Adaptation of Language Models [88.8947656843812]
  Large language models encode impressively broad world knowledge in their parameters. However, the knowledge in static language models falls out of date, limiting the model's effective "shelf life"
  arXiv  Detail & Related papers  (2023-05-24T11:56:20Z)
• Implicit Parameter-free Online Learning with Truncated Linear Models [51.71216912089413]
  parameter-free algorithms are online learning algorithms that do not require setting learning rates. We propose new parameter-free algorithms that can take advantage of truncated linear models through a new update that has an "implicit" flavor. Based on a novel decomposition of the regret, the new update is efficient, requires only one gradient at each step, never overshoots the minimum of the truncated model, and retains the favorable parameter-free properties.
  arXiv  Detail & Related papers  (2022-03-19T13:39:49Z)
• Learning to Minimize the Remainder in Supervised Learning [37.481538167715755]
  We propose a new learning approach, namely gradient adjustment learning (GAL), to leverage the knowledge learned from the past training to adjust gradients. The proposed GAL is model- and-agnostic, and is easy to adapt to the standard learning framework. The experiments show that the proposed GAL consistently enhances the evaluated models, whereas the ablation studies validate various aspects of the proposed GAL.
  arXiv  Detail & Related papers  (2022-01-23T06:31:23Z)
• Distributionally Robust Semi-Supervised Learning Over Graphs [68.29280230284712]
  Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. Despite their success in practice, most of existing methods are unable to handle graphs with uncertain nodal attributes. Challenges also arise due to distributional uncertainties associated with data acquired by noisy measurements. A distributionally robust learning framework is developed, where the objective is to train models that exhibit quantifiable robustness against perturbations.
  arXiv  Detail & Related papers  (2021-10-20T14:23:54Z)
• 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)
• Cold-start Active Learning through Self-supervised Language Modeling [15.551710499866239]
  Active learning aims to reduce annotation costs by choosing the most critical examples to label. With BERT, we develop a simple strategy based on the masked language modeling loss. Compared to other baselines, our approach reaches higher accuracy within less sampling iterations and time.
  arXiv  Detail & Related papers  (2020-10-19T14:09:17Z)

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.