NoT: Federated Unlearning via Weight Negation

• URL: http://arxiv.org/abs/2503.05657v1
• Date: Fri, 07 Mar 2025 18:19:19 GMT
• Title: NoT: Federated Unlearning via Weight Negation
• Authors: Yasser H. Khalil, Leo Brunswic, Soufiane Lamghari, Xu Li, Mahdi Beitollahi, Xi Chen,
• Abstract summary: Federated unlearning (FU) aims to remove a participant's data contributions from a trained federated learning (FL) model, ensuring privacy and regulatory compliance.<n>Traditional FU methods often depend on auxiliary storage on either the client or server side or require direct access to the data targeted for removal.<n>We propose NoT, a novel and efficient FU algorithm based on weight negation (multiplying by -1), which circumvents the need for additional storage and access to the target data.
• Score: 8.231565480337803
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated unlearning (FU) aims to remove a participant's data contributions from a trained federated learning (FL) model, ensuring privacy and regulatory compliance. Traditional FU methods often depend on auxiliary storage on either the client or server side or require direct access to the data targeted for removal-a dependency that may not be feasible if the data is no longer available. To overcome these limitations, we propose NoT, a novel and efficient FU algorithm based on weight negation (multiplying by -1), which circumvents the need for additional storage and access to the target data. We argue that effective and efficient unlearning can be achieved by perturbing model parameters away from the set of optimal parameters, yet being well-positioned for quick re-optimization. This technique, though seemingly contradictory, is theoretically grounded: we prove that the weight negation perturbation effectively disrupts inter-layer co-adaptation, inducing unlearning while preserving an approximate optimality property, thereby enabling rapid recovery. Experimental results across three datasets and three model architectures demonstrate that NoT significantly outperforms existing baselines in unlearning efficacy as well as in communication and computational efficiency.

Related papers

• SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models [51.74498855100541]
  Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
  arXiv  Detail & Related papers  (2025-08-07T03:50:48Z)
• Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data [73.04828796123581]
  Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs)<n>We introduce Discriminative Fine-Tuning (DFT), an improved variant of SFT, which mitigates the burden of collecting human-labeled preference data.<n>Our contributions include: (i) a discriminative probabilistic framework for fine-tuning LLMs by explicitly modeling the discriminative likelihood of an answer among all possible outputs given an input; (ii) efficient algorithms to optimize this discriminative likelihood; and (iii) extensive experiments demonstrating DFT's effectiveness
  arXiv  Detail & Related papers  (2025-02-25T22:38:55Z)
• FedUHB: Accelerating Federated Unlearning via Polyak Heavy Ball Method [17.720414283108727]
  Federated unlearning (FU) has been developed to efficiently eliminate the influence of specific data from the model. We propose FedUHB, a novel exact unlearning approach that leverages the Polyak heavy ball optimization technique. Our experiments show that FedUHB not only enhances unlearning efficiency but also preserves robust model performance after unlearning.
  arXiv  Detail & Related papers  (2024-11-17T11:08:49Z)
• Towards Robust and Cost-Efficient Knowledge Unlearning for Large Language Models [25.91643745340183]
  Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora. This poses risk of privacy and copyright violations, highlighting the need for efficient machine unlearning methods. We propose two novel techniques for robust and efficient unlearning for LLMs.
  arXiv  Detail & Related papers  (2024-08-13T04:18:32Z)
• Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning [28.059563581973432]
  Large Language Models (LLMs) often have sensitive, private, or copyrighted data during pre-training. LLMs unlearning aims to eliminate the influence of undesirable data from the pre-trained model. We propose Negative Preference Optimization (NPO) as a simple alignment-inspired method that could efficiently unlearn a target dataset.
  arXiv  Detail & Related papers  (2024-04-08T21:05:42Z)
• Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
  Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data. This process might suffer from privacy issues and violations of data protection regulations. We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
  arXiv  Detail & Related papers  (2023-10-31T03:35:59Z)
• Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization [71.87335804334616]
  Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. The training process of Large Language Models (LLMs) generally incurs the update of significant parameters. This paper proposes an efficient partial prompt tuning approach to improve performance and efficiency simultaneously.
  arXiv  Detail & Related papers  (2023-10-23T16:37:59Z)
• Recommendation Unlearning via Influence Function [42.4931807753579]
  We propose a new Influence Function-based Recommendation Unlearning (IFRU) framework, which efficiently updates the model without retraining. IFRU achieves more than 250 times acceleration compared to retraining-based methods with recommendation performance comparable to full retraining.
  arXiv  Detail & Related papers  (2023-07-05T09:42:51Z)
• Scaling Laws Beyond Backpropagation [64.0476282000118]
  We study the ability of Direct Feedback Alignment to train causal decoder-only Transformers efficiently. We find that DFA fails to offer more efficient scaling than backpropagation.
  arXiv  Detail & Related papers  (2022-10-26T10:09:14Z)
• Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding [62.17020485045456]
  It is commonly assumed in semi-supervised learning (SSL) that the unlabeled data are drawn from the same distribution as that of the labeled ones. We propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized.
  arXiv  Detail & Related papers  (2022-05-02T16:09:17Z)
• DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation [57.358212277226315]
  In imitation learning from observation IfO, a learning agent seeks to imitate a demonstrating agent using only observations of the demonstrated behavior without access to the control signals generated by the demonstrator. Recent methods based on adversarial imitation learning have led to state-of-the-art performance on IfO problems, but they typically suffer from high sample complexity due to a reliance on data-inefficient, model-free reinforcement learning algorithms. This issue makes them impractical to deploy in real-world settings, where gathering samples can incur high costs in terms of time, energy, and risk. We propose a more data-efficient IfO algorithm
  arXiv  Detail & Related papers  (2021-03-31T23:46:32Z)
• Toward Understanding the Influence of Individual Clients in Federated Learning [52.07734799278535]
  Federated learning allows clients to jointly train a global model without sending their private data to a central server. We defined a new notion called em-Influence, quantify this influence over parameters, and proposed an effective efficient model to estimate this metric.
  arXiv  Detail & Related papers  (2020-12-20T14:34:36Z)
• Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback [28.30678887024847]
  How to assign confidence weights and how to handle the large number of unobserved data are two key problems for implicit recommendation models. We propose a fast adaptively weighted matrix factorization (FAWMF) based on variational auto-encoder. Experiments on real-world datasets demonstrate the superiority of the proposed FAWMF and its learning algorithm fBGD.
  arXiv  Detail & Related papers  (2020-03-04T04:50:44Z)

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.