Delete and Retain: Efficient Unlearning for Document Classification

• URL: http://arxiv.org/abs/2512.13711v1
• Date: Sat, 06 Dec 2025 18:57:06 GMT
• Title: Delete and Retain: Efficient Unlearning for Document Classification
• Authors: Aadya Goel, Mayuri Sridhar,
• Abstract summary: Hessian Reassignment is a two-step, model-agnostic solution for class unlearning in document classification.<n>On standard text benchmarks, Hessian Reassignment retained-class accuracy close to full-without-class while running orders of magnitude faster.<n>Results demonstrate a practical, principled path to efficient class unlearning in document classification.
• Score: 1.0026496861838448
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine unlearning aims to efficiently remove the influence of specific training data from a model without full retraining. While much progress has been made in unlearning for LLMs, document classification models remain relatively understudied. In this paper, we study class-level unlearning for document classifiers and present Hessian Reassignment, a two-step, model-agnostic solution. First, we perform a single influence-style update that subtracts the contribution of all training points from the target class by solving a Hessian-vector system with conjugate gradients, requiring only gradient and Hessian-vector products. Second, in contrast to common unlearning baselines that randomly reclassify deleted-class samples, we enforce a decision-space guarantee via Top-1 classification. On standard text benchmarks, Hessian Reassignment achieves retained-class accuracy close to full retrain-without-class while running orders of magnitude faster. Additionally, it consistently lowers membership-inference advantage on the removed class, measured with pooled multi-shadow attacks. These results demonstrate a practical, principled path to efficient class unlearning in document classification.

Related papers

• GLiClass: Generalist Lightweight Model for Sequence Classification Tasks [49.2639069781367]
  We propose GLiClass, a novel method that adapts the GLiNER architecture for sequence classification tasks.<n>Our approach achieves strong accuracy and efficiency comparable to embedding-based methods, while maintaining the flexibility needed for zero-shot and few-shot learning scenarios.
  arXiv  Detail & Related papers  (2025-08-11T06:22:25Z)
• CBR - Boosting Adaptive Classification By Retrieval of Encrypted Network Traffic with Out-of-distribution [9.693391036125908]
  One of the common approaches is using Machine learning or Deep Learning-based solutions on a fixed number of classes. One of the solutions for handling unknown classes is to retrain the model, however, retraining models every time they become obsolete is both resource and time-consuming. In this paper, we introduce Adaptive Classification By Retrieval CBR, a novel approach for encrypted network traffic classification.
  arXiv  Detail & Related papers  (2024-03-17T13:14:09Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model [73.80068155830708]
  We present an extensive analysis for continual learning on a pre-trained model (CLPM) We propose a simple but extremely effective approach named Slow Learner with Alignment (SLCA) Across a variety of scenarios, our proposal provides substantial improvements for CLPM.
  arXiv  Detail & Related papers  (2023-03-09T08:57:01Z)
• Prototypical quadruplet for few-shot class incremental learning [24.814045065163135]
  We propose a novel method that improves classification robustness by identifying a better embedding space using an improved contrasting loss. Our approach retains previously acquired knowledge in the embedding space, even when trained with new classes. We demonstrate the effectiveness of our method by showing that the embedding space remains intact after training the model with new classes and outperforms existing state-of-the-art algorithms in terms of accuracy across different sessions.
  arXiv  Detail & Related papers  (2022-11-05T17:19:14Z)
• Evolving Multi-Label Fuzzy Classifier [5.53329677986653]
  Multi-label classification has attracted much attention in the machine learning community to address the problem of assigning single samples to more than one class at the same time. We propose an evolving multi-label fuzzy classifier (EFC-ML) which is able to self-adapt and self-evolve its structure with new incoming multi-label samples in an incremental, single-pass manner.
  arXiv  Detail & Related papers  (2022-03-29T08:01:03Z)
• You Only Need End-to-End Training for Long-Tailed Recognition [8.789819609485225]
  Cross-entropy loss tends to produce highly correlated features on imbalanced data. We propose two novel modules, Block-based Relatively Balanced Batch Sampler (B3RS) and Batch Embedded Training (BET) Experimental results on the long-tailed classification benchmarks, CIFAR-LT and ImageNet-LT, demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2021-12-11T11:44:09Z)
• Self-Supervised Class Incremental Learning [51.62542103481908]
  Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new. In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time.
  arXiv  Detail & Related papers  (2021-11-18T06:58:19Z)
• Class-Incremental Learning with Generative Classifiers [6.570917734205559]
  We propose a new strategy for class-incremental learning: generative classification. Our proposal is to learn the joint distribution p(x,y), factorized as p(x|y)p(y), and to perform classification using Bayes' rule. As a proof-of-principle, here we implement this strategy by training a variational autoencoder for each class to be learned.
  arXiv  Detail & Related papers  (2021-04-20T16:26:14Z)
• Improving Calibration for Long-Tailed Recognition [68.32848696795519]
  We propose two methods to improve calibration and performance in such scenarios. For dataset bias due to different samplers, we propose shifted batch normalization. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-01T13:55:21Z)
• Fast Few-Shot Classification by Few-Iteration Meta-Learning [173.32497326674775]
  We introduce a fast optimization-based meta-learning method for few-shot classification. Our strategy enables important aspects of the base learner objective to be learned during meta-training. We perform a comprehensive experimental analysis, demonstrating the speed and effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-10-01T15:59:31Z)

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.