Pre-training for Recommendation Unlearning

TL;DR

This paper introduces UnlearnRec, a pre-training approach for GNN-based recommender systems that enables efficient unlearning of user data, significantly reducing retraining time while maintaining recommendation quality.

Contribution

We propose UnlearnRec, a model-agnostic pre-training paradigm with an Influence Encoder that facilitates fast, effective unlearning without full retraining.

Findings

UnlearnRec achieves over 10x speedup compared to retraining.

The method maintains recommendation performance after unlearning.

Extensive benchmarks validate the effectiveness of UnlearnRec.

Abstract

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.