# Pre-training for Recommendation Unlearning

arXiv: https://arxiv.org/abs/2505.22649 · HTML: https://mlsanity.com/paper/2505.22649/

## 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 25 of its 37 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Self-supervised Graph Learning for Recommendation](https://mlsanity.com/paper/2010.10783/) (2020)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2112.08679/) (2021)
- [A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions](https://mlsanity.com/paper/2109.12843/) (2021)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [Deep Learning based Recommender System: A Survey and New Perspectives](https://mlsanity.com/paper/1707.07435/) (2017)
- [Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach](https://mlsanity.com/paper/2001.10167/) (2020)
- [Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning](https://mlsanity.com/paper/2202.06200/) (2022)
- [Recommendation Unlearning](https://mlsanity.com/paper/2201.06820/) (2022)
- [GIF: A General Graph Unlearning Strategy via Influence Function](https://mlsanity.com/paper/2304.02835/) (2023)
- [Automated Self-Supervised Learning for Recommendation](https://mlsanity.com/paper/2303.07797/) (2023)
- [Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation](https://mlsanity.com/paper/2203.11491/) (2022)
- [Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filtering](https://mlsanity.com/paper/2210.11054/) (2022)
- [Recommendation Unlearning via Influence Function](https://mlsanity.com/paper/2307.02147/) (2023)
- [RecDiff: Diffusion Model for Social Recommendation](https://mlsanity.com/paper/2406.01629/) (2024)
- [LightGNN: Simple Graph Neural Network for Recommendation](https://mlsanity.com/paper/2501.03228/) (2025)

## Abstract (arXiv)

Modern recommender systems powered by Graph Neural Networks (GNNs) excel at modeling complex user-item interactions, yet increasingly face scenarios requiring selective forgetting of training data. Beyond user requests to remove specific interactions due to privacy concerns or preference changes, regulatory frameworks mandate recommender systems' ability to eliminate the influence of certain user data from models. This recommendation unlearning challenge presents unique difficulties as removing connections within interaction graphs creates ripple effects throughout the model, potentially impacting recommendations for numerous users. Traditional approaches suffer from significant drawbacks: fragmentation methods damage graph structure and diminish performance, while influence function techniques make assumptions that may not hold in complex GNNs, particularly with self-supervised or random architectures. To address these limitations, we propose a novel model-agnostic pre-training paradigm UnlearnRec that prepares systems for efficient unlearning operations. Our Influence Encoder takes unlearning requests together with existing model parameters and directly produces updated parameters of unlearned model with little fine-tuning, avoiding complete retraining while preserving model performance characteristics. Extensive evaluation on public benchmarks demonstrates that our method delivers exceptional unlearning effectiveness while providing more than 10x speedup compared to retraining approaches. We release our method implementation at: https://github.com/HKUDS/UnlearnRec.