Learning to Fast Unrank in Collaborative Filtering Recommendation

TL;DR

This paper introduces L2UnRank, a fast and effective unranking method for recommendation systems that reduces target item rankings efficiently while preserving recommendation quality and ensuring privacy.

Contribution

The paper proposes a novel unranking approach tailored for ranking-oriented recommendation systems, achieving significant speedup and effectiveness over existing unlearning methods.

Findings

L2UnRank achieves a 50x speedup over existing methods.

It maintains recommendation quality comparable to retraining.

It is model-agnostic and effective across multiple datasets.

Abstract

Modern data-driven recommendation systems risk memorizing sensitive user behavioral patterns, raising privacy concerns. Existing recommendation unlearning methods, while capable of removing target data influence, suffer from inefficient unlearning speed and degraded performance, failing to meet real-time unlearning demands. Considering the ranking-oriented nature of recommendation systems, we present unranking, the process of reducing the ranking positions of target items while ensuring the formal guarantees of recommendation unlearning. To achieve efficient unranking, we propose Learning to Fast Unrank in Collaborative Filtering Recommendation (L2UnRank), which operates through three key stages: (a) identifying the influenced scope via interaction-based p-hop propagation, (b) computing structural and semantic influences for entities within this scope, and (c) performing efficient, ranking-aware parameter updates guided by influence information. Extensive experiments across multiple datasets and backbone models demonstrate L2UnRank's model-agnostic nature, achieving state-of-the-art unranking effectiveness and maintaining recommendation quality comparable to retraining, while also delivering a 50x speedup over existing methods. Codes are available at https://github.com/Juniper42/L2UnRank.