Obliviate: Efficient Unlearning in Recommender Systems

• URL: http://arxiv.org/abs/2607.22665v1
• Date: Tue, 30 Jun 2026 05:52:32 GMT
• Title: Obliviate: Efficient Unlearning in Recommender Systems
• Abstract summary: Obliviate is an efficient two-stage unlearning framework for recommender systems.<n>It achieves high unlearning completeness while maintaining good utility.<n>It is a practical and scalable solution for large-scale recommender systems.
• Score: 3.725417596576278
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine unlearning is becoming increasingly critical in the context of data privacy regulations, particularly for recommendation systems that are directly trained on user interaction data. The goal of this work is to remove requested interaction data and their downstream influence from trained model while preserving recommendation quality, and to do so without incurring the substantial computational cost of full retraining. Existing approaches exhibit several limitations, including limited unlearning completeness and degradation in recommendation performance, while having substantial computational overhead. In this paper, we propose Obliviate, an efficient two-stage unlearning framework for recommender systems that achieves high unlearning completeness while maintaining good utility. In the first stage, we introduce a Low-Rank Unlearning Adapter (LUA), which employs a lightweight Hessian proxy to enable curvature-aware and efficient unlearning through localized low-rank adapters rather than full parameters. In the second stage, we propose Locality-Aware Calibration (LAC), a lightweight refinement stage that updates only the adapter parameters to improve the performance by enforcing unlearning via ranking-based objectives while preserving utility through knowledge distillation. Extensive empirical evaluations demonstrate that Obliviate achieves high level of forgetting with minimal loss in recommendation quality and at significantly reduced computational cost, offering a practical and scalable solution for large-scale recommender systems.

Related papers

• ERASE -- A Real-World Aligned Benchmark for Unlearning in Recommender Systems [53.62904488040001]
  We present ERASE, a large-scale benchmark for machine unlearning in recommender systems.<n> ERASE spans three core tasks -- collaborative filtering, session-based recommendation, and next-basket recommendation.<n>It includes unlearning scenarios inspired by real-world applications, such as sequentially removing sensitive interactions or spam.
  arXiv  Detail & Related papers  (2026-03-09T13:00:23Z)
• AdaSwitch: Adaptive Switching Generation for Knowledge Distillation [58.647880811071495]
  Small language models (SLMs) are crucial for applications with strict latency and computational constraints.<n>We propose AdaSwitch, a novel approach that combines on-policy and off-policy generation at the token level.<n>AdaSwitch consistently improves accuracy, offering a practical and effective method for distilling SLMs with acceptable additional overhead.
  arXiv  Detail & Related papers  (2025-10-09T06:38:37Z)
• Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward [54.708851958671794]
  We propose a Data-Efficient Policy Optimization pipeline that combines optimized strategies for both offline and online data selection.<n>In offline phase, we curate a high-quality subset of training samples based on diversity, influence, and appropriate difficulty.<n>During online RLVR training, we introduce a sample-level explorability metric to dynamically filter samples with low exploration potential.
  arXiv  Detail & Related papers  (2025-09-01T10:04:20Z)
• Towards a Real-World Aligned Benchmark for Unlearning in Recommender Systems [49.766845975588275]
  We propose a set of design desiderata and research questions to guide the development of a more realistic benchmark for unlearning in recommender systems.<n>We argue for an unlearning setup that reflects the sequential, time-sensitive nature of real-world deletion requests.<n>We present a preliminary experiment in a next-basket recommendation setting based on our proposed desiderata and find that unlearning also works for sequential recommendation models.
  arXiv  Detail & Related papers  (2025-08-23T16:05:40Z)
• Curriculum Approximate Unlearning for Session-based Recommendation [56.86137487298901]
  Approximate unlearning for session-based recommendation refers to eliminating the influence of specific training samples from the recommender without retraining.<n> Gradient ascent (GA) is a representative method to conduct approximate unlearning.<n>We introduce CAU, a curriculum approximate unlearning framework tailored to session-based recommendation.
  arXiv  Detail & Related papers  (2025-08-21T05:52:28Z)
• UniErase: Towards Balanced and Precise Unlearning in Language Models [69.04923022755547]
  Large language models (LLMs) require iterative updates to address the outdated information problem.<n>UniErase is a novel unlearning framework that demonstrates precision and balanced performances between knowledge unlearning and ability retaining.
  arXiv  Detail & Related papers  (2025-05-21T15:53:28Z)
• Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs [25.91643745340183]
  Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora.<n>This poses risk of privacy and copyright violations, highlighting the need for efficient machine unlearning methods.<n>We propose Low-rank Knowledge Unlearning (LoKU), a novel framework that enables robust and efficient unlearning for LLMs.
  arXiv  Detail & Related papers  (2024-08-13T04:18:32Z)
• Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios [18.73206066109299]
  Mini-Unlearning is a novel approach that capitalizes on a critical observation: unlearned parameters correlate with retrained parameters through contraction mapping. This lightweight, scalable method significantly enhances model accuracy and strengthens resistance to membership inference attacks. Our experiments demonstrate that Mini-Unlearning not only works under higher unlearning ratios but also outperforms existing techniques in both accuracy and security.
  arXiv  Detail & Related papers  (2024-06-24T01:43:30Z)
• Post-Training Attribute Unlearning in Recommender Systems [37.67195112898097]
  Existing studies predominantly use training data, i.e., model inputs, as unlearning target. We name this unseen information as textitattribute and treat it as unlearning target. To protect the sensitive attribute of users, Attribute Unlearning (AU) aims to make target attributes indistinguishable.
  arXiv  Detail & Related papers  (2024-03-11T14:02:24Z)
• Adaptive Dense-to-Sparse Paradigm for Pruning Online Recommendation System with Non-Stationary Data [13.080986170257782]
  Pruning is an effective technique that reduces both memory and compute demand for model inference. This work presents an adaptive dense to sparse paradigm equipped with a novel pruning algorithm for pruning a large scale recommendation system with non-stationary data distribution.
  arXiv  Detail & Related papers  (2020-10-16T22:33:14Z)

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.