Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases

• URL: http://arxiv.org/abs/2405.14020v1
• Date: Wed, 22 May 2024 21:54:05 GMT
• Title: Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases
• Authors: Ling Han, Hao Huang, Dustin Scheinost, Mary-Anne Hartley, María Rodríguez Martínez,
• Abstract summary: We present Unlearning Information Bottleneck (UIB), a novel information-theoretic framework designed to enhance the process of machine unlearning. By proposing a variational upper bound, we recalibrate the model parameters through a dynamic prior that integrates changes in data distribution with an affordable computational cost. Our experiments across various datasets, models, and unlearning methods demonstrate that our approach effectively removes systematic patterns and biases while maintaining the performance of models post-unlearning.
• Score: 6.936871609178494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional approaches typically assume that data variations are random, which makes it difficult to adjust the model parameters accurately to remove patterns and characteristics from unlearned data. In this work, we present Unlearning Information Bottleneck (UIB), a novel information-theoretic framework designed to enhance the process of machine unlearning that effectively leverages the influence of systematic patterns and biases for parameter adjustment. By proposing a variational upper bound, we recalibrate the model parameters through a dynamic prior that integrates changes in data distribution with an affordable computational cost, allowing efficient and accurate removal of outdated or unwanted data patterns and biases. Our experiments across various datasets, models, and unlearning methods demonstrate that our approach effectively removes systematic patterns and biases while maintaining the performance of models post-unlearning.

Related papers

• Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA [15.542668474378633]
  We propose a novel and efficient machine unlearning method on pre-trained models. We leverage LoRA to decompose the model's intermediate features into pre-trained features and residual features. The method aims to learn the zero residuals on the retained set and shifted residuals on the unlearning set.
  arXiv  Detail & Related papers  (2024-11-13T08:56:35Z)
• 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)
• 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)
• CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning [55.733193075728096]
  Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. We propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data.
  arXiv  Detail & Related papers  (2022-02-11T13:49:51Z)
• A Framework for Machine Learning of Model Error in Dynamical Systems [7.384376731453594]
  We present a unifying framework for blending mechanistic and machine-learning approaches to identify dynamical systems from data. We cast the problem in both continuous- and discrete-time, for problems in which the model error is memoryless and in which it has significant memory. We find that hybrid methods substantially outperform solely data-driven approaches in terms of data hunger, demands for model complexity, and overall predictive performance.
  arXiv  Detail & Related papers  (2021-07-14T12:47:48Z)
• Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components [52.77024349608834]
  We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data is noisy partial measurements. We show that by using partial measurements of the state of the dynamical system, we can train a machine learning model to improve predictions made by an imperfect knowledge-based model.
  arXiv  Detail & Related papers  (2021-02-15T19:56:48Z)
• Model-Based Deep Learning [155.063817656602]
  Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance. We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.
  arXiv  Detail & Related papers  (2020-12-15T16:29:49Z)
• Knowledge-Based Learning of Nonlinear Dynamics and Chaos [3.673994921516517]
  We present a universal learning framework for extracting predictive models from nonlinear systems based on observations. Our framework can readily incorporate first principle knowledge because it naturally models nonlinear systems as continuous-time systems.
  arXiv  Detail & Related papers  (2020-10-07T13:50:13Z)
• How Training Data Impacts Performance in Learning-based Control [67.7875109298865]
  This paper derives an analytical relationship between the density of the training data and the control performance. We formulate a quality measure for the data set, which we refer to as $rho$-gap. We show how the $rho$-gap can be applied to a feedback linearizing control law.
  arXiv  Detail & Related papers  (2020-05-25T12:13:49Z)
• From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication Systems [40.427909614453526]
  Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. With a meta-trained inductive bias, training of a machine learning model can be potentially carried out with reduced training data and/or time complexity. This paper provides a high-level introduction to meta-learning with applications to communication systems.
  arXiv  Detail & Related papers  (2020-01-05T12:54:41Z)

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.