# Obliviate: Efficient Unlearning in Recommender Systems

arXiv: https://arxiv.org/abs/2607.22665 · HTML: https://mlsanity.com/paper/2607.22665/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 23 of 23)

- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [How to Escape Saddle Points Efficiently](https://mlsanity.com/paper/1703.00887/) (2017)
- [What makes unlearning hard and what to do about it](https://mlsanity.com/paper/2406.01257/) (2024)
- [Recommendation Unlearning](https://mlsanity.com/paper/2201.06820/) (2022)
- [Datasets for Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2402.18041/) (2024)
- [Selective and Collaborative Influence Function for Efficient Recommendation Unlearning](https://mlsanity.com/paper/2304.10199/) (2023)
- [Recommendation Unlearning via Influence Function](https://mlsanity.com/paper/2307.02147/) (2023)
- [Piecewise Strong Convexity of Neural Networks](https://mlsanity.com/paper/1810.12805/) (2018)
- [Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations](https://mlsanity.com/paper/2302.06676/) (2023)
- [Forgetting Fast in Recommender Systems](https://mlsanity.com/paper/2208.06875/) (2022)
- [Recommendation Unlearning via Matrix Correction](https://mlsanity.com/paper/2307.15960/) (2023)
- [CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence](https://mlsanity.com/paper/2408.14393/) (2024)
- [Contemporary Recommendation Systems on Big Data and Their Applications: A Survey](https://mlsanity.com/paper/2206.02631/) (2022)
- [On Newton's Method to Unlearn Neural Networks](https://mlsanity.com/paper/2406.14507/) (2024)
- [Local Strong Convexity of Source Localization and Error Bound for Target Tracking under Time-of-Arrival Measurements](https://mlsanity.com/paper/2112.11045/) (2021)
- [Generalized Low-Rank Update: Model Parameter Bounds for Low-Rank Training Data Modifications](https://mlsanity.com/paper/2306.12670/) (2023)

## Abstract (arXiv)

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.