Debiasing Machine Unlearning with Counterfactual Examples

• URL: http://arxiv.org/abs/2404.15760v1
• Date: Wed, 24 Apr 2024 09:33:10 GMT
• Title: Debiasing Machine Unlearning with Counterfactual Examples
• Authors: Ziheng Chen, Jia Wang, Jun Zhuang, Abbavaram Gowtham Reddy, Fabrizio Silvestri, Jin Huang, Kaushiki Nag, Kun Kuang, Xin Ning, Gabriele Tolomei,
• Abstract summary: We analyze the causal factors behind the unlearning process and mitigate biases at both data and algorithmic levels. We introduce an intervention-based approach, where knowledge to forget is erased with a debiased dataset. Our method outperforms existing machine unlearning baselines on evaluation metrics.
• Score: 31.931056076782202
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The right to be forgotten (RTBF) seeks to safeguard individuals from the enduring effects of their historical actions by implementing machine-learning techniques. These techniques facilitate the deletion of previously acquired knowledge without requiring extensive model retraining. However, they often overlook a critical issue: unlearning processes bias. This bias emerges from two main sources: (1) data-level bias, characterized by uneven data removal, and (2) algorithm-level bias, which leads to the contamination of the remaining dataset, thereby degrading model accuracy. In this work, we analyze the causal factors behind the unlearning process and mitigate biases at both data and algorithmic levels. Typically, we introduce an intervention-based approach, where knowledge to forget is erased with a debiased dataset. Besides, we guide the forgetting procedure by leveraging counterfactual examples, as they maintain semantic data consistency without hurting performance on the remaining dataset. Experimental results demonstrate that our method outperforms existing machine unlearning baselines on evaluation metrics.

Related papers

• Model Debiasing by Learnable Data Augmentation [19.625915578646758]
  This paper proposes a novel 2-stage learning pipeline featuring a data augmentation strategy able to regularize the training. Experiments on synthetic and realistic biased datasets show state-of-the-art classification accuracy, outperforming competing methods.
  arXiv  Detail & Related papers  (2024-08-09T09:19:59Z)
• Data augmentation and explainability for bias discovery and mitigation in deep learning [0.0]
  This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data and models, with a particular focus on bias in machine learning pipelines. The next chapter outlines a taxonomy and methods of Explainable AI as a way to justify predictions and control and improve the model.
  arXiv  Detail & Related papers  (2023-08-18T11:02:27Z)
• Fair Machine Unlearning: Data Removal while Mitigating Disparities [5.724350004671127]
  Right to be forgotten is core principle outlined by EU's General Regulation. "Forgetting" can be naively achieved by retraining on remaining data. "Unlearning" impacts other properties critical to real-world applications such as fairness.
  arXiv  Detail & Related papers  (2023-07-27T10:26:46Z)
• Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers [71.70205894168039]
  We consider instance-wise unlearning, of which the goal is to delete information on a set of instances from a pre-trained model. We propose two methods that reduce forgetting on the remaining data: 1) utilizing adversarial examples to overcome forgetting at the representation-level and 2) leveraging weight importance metrics to pinpoint network parameters guilty of propagating unwanted information.
  arXiv  Detail & Related papers  (2023-01-27T07:53:50Z)
• Simultaneous Improvement of ML Model Fairness and Performance by Identifying Bias in Data [1.76179873429447]
  We propose a data preprocessing technique that can detect instances ascribing a specific kind of bias that should be removed from the dataset before training. In particular, we claim that in the problem settings where instances exist with similar feature but different labels caused by variation in protected attributes, an inherent bias gets induced in the dataset.
  arXiv  Detail & Related papers  (2022-10-24T13:04:07Z)
• Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques [19.252319300590656]
  Existing techniques for mitigating dataset bias often leverage a biased model to identify biased instances. The role of these biased instances is then reduced during the training of the main model to enhance its robustness to out-of-distribution data. In this paper, we show that this assumption does not hold in general.
  arXiv  Detail & Related papers  (2021-09-01T10:25:46Z)
• Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization [77.8735802150511]
  We propose a cross-sample adversarial debiasing (CSAD) method to remove the bias information misused by the target task. The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator. We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-08-11T21:17:02Z)
• 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)
• Learning from others' mistakes: Avoiding dataset biases without modeling them [111.17078939377313]
  State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended task. Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available. We show a method for training models that learn to ignore these problematic correlations.
  arXiv  Detail & Related papers  (2020-12-02T16:10:54Z)
• 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)
• Towards Robustifying NLI Models Against Lexical Dataset Biases [94.79704960296108]
  This paper explores both data-level and model-level debiasing methods to robustify models against lexical dataset biases. First, we debias the dataset through data augmentation and enhancement, but show that the model bias cannot be fully removed via this method. The second approach employs a bag-of-words sub-model to capture the features that are likely to exploit the bias and prevents the original model from learning these biased features.
  arXiv  Detail & Related papers  (2020-05-10T17:56:10Z)

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.