FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning

• URL: http://arxiv.org/abs/2601.18650v1
• Date: Mon, 26 Jan 2026 16:21:01 GMT
• Title: FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
• Authors: Liheng Yu, Zhe Zhao, Yuxuan Wang, Pengkun Wang, Binwu Wang, Yang Wang,
• Abstract summary: FaLW is a plug-and-play, instance-wise dynamic loss reweighting method.<n>It assesses the unlearning state of each sample by comparing its predictive probability to the distribution of unseen data from the same class.<n>Experiments demonstrate that FaLW achieves superior performance.
• Score: 24.734154431191538
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be forgotten". However, existing research predominantly evaluates unlearning methods on relatively balanced forget sets. This overlooks a common real-world scenario where data to be forgotten, such as a user's activity records, follows a long-tailed distribution. Our work is the first to investigate this critical research gap. We find that in such long-tailed settings, existing methods suffer from two key issues: \textit{Heterogeneous Unlearning Deviation} and \textit{Skewed Unlearning Deviation}. To address these challenges, we propose FaLW, a plug-and-play, instance-wise dynamic loss reweighting method. FaLW innovatively assesses the unlearning state of each sample by comparing its predictive probability to the distribution of unseen data from the same class. Based on this, it uses a forgetting-aware reweighting scheme, modulated by a balancing factor, to adaptively adjust the unlearning intensity for each sample. Extensive experiments demonstrate that FaLW achieves superior performance. Code is available at \textbf{Supplementary Material}.

Related papers

• Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias [18.802863823537542]
  CUPID is a new unlearning framework inspired by the observation that samples with different biases exhibit distinct loss landscape sharpness.<n>Our method first partitions the forget set into causal- and bias-approximated subsets based on sample sharpness, then disentangles model parameters into causal and bias pathways.
  arXiv  Detail & Related papers  (2026-02-25T10:48:51Z)
• Data Unlearning in Diffusion Models [44.99833362998488]
  General-purpose machine unlearning techniques were found to be either unstable or failed to unlearn data.<n>We propose a family of new loss functions called Subtracted Importance Sampled Scores (SISS) that utilize importance sampling and are the first method to unlearn data with theoretical guarantees.
  arXiv  Detail & Related papers  (2025-03-02T21:36:04Z)
• Attribute-to-Delete: Machine Unlearning via Datamodel Matching [65.13151619119782]
  Machine unlearning -- efficiently removing a small "forget set" training data on a pre-divertrained machine learning model -- has recently attracted interest. Recent research shows that machine unlearning techniques do not hold up in such a challenging setting.
  arXiv  Detail & Related papers  (2024-10-30T17:20:10Z)
• Learning from Neighbors: Category Extrapolation for Long-Tail Learning [62.30734737735273]
  We offer a novel perspective on long-tail learning, inspired by an observation: datasets with finer granularity tend to be less affected by data imbalance.<n>We introduce open-set auxiliary classes that are visually similar to existing ones, aiming to enhance representation learning for both head and tail classes.<n>To prevent the overwhelming presence of auxiliary classes from disrupting training, we introduce a neighbor-silencing loss.
  arXiv  Detail & Related papers  (2024-10-21T13:06:21Z)
• Debiasing Machine Unlearning with Counterfactual Examples [31.931056076782202]
  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.
  arXiv  Detail & Related papers  (2024-04-24T09:33:10Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [93.90047628101155]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks.<n>To address this, some methods propose replaying data from previous tasks during new task learning.<n>However, it is not expected in practice due to memory constraints and data privacy issues.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Robust Machine Learning by Transforming and Augmenting Imperfect Training Data [6.928276018602774]
  This thesis explores several data sensitivities of modern machine learning. We first discuss how to prevent ML from codifying prior human discrimination measured in the training data. We then discuss the problem of learning from data containing spurious features, which provide predictive fidelity during training but are unreliable upon deployment.
  arXiv  Detail & Related papers  (2023-12-19T20:49:28Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• 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)
• Deep F-measure Maximization for End-to-End Speech Understanding [52.36496114728355]
  We propose a differentiable approximation to the F-measure and train the network with this objective using standard backpropagation. We perform experiments on two standard fairness datasets, Adult, Communities and Crime, and also on speech-to-intent detection on the ATIS dataset and speech-to-image concept classification on the Speech-COCO dataset. In all four of these tasks, F-measure results in improved micro-F1 scores, with absolute improvements of up to 8% absolute, as compared to models trained with the cross-entropy loss function.
  arXiv  Detail & Related papers  (2020-08-08T03:02:27Z)

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.