Adversarial Personalized Ranking for Recommendation

TL;DR

This paper introduces Adversarial Personalized Ranking (APR), a robust optimization framework that enhances pairwise ranking models like BPR for recommendation systems by incorporating adversarial training, leading to improved accuracy and generalization.

Contribution

The paper proposes APR, a novel adversarial training method for personalized ranking that significantly improves robustness and recommendation performance over traditional BPR.

Findings

APR outperforms BPR with an 11.2% relative improvement.

It achieves state-of-the-art results on three real-world datasets.

Adversarial training enhances model robustness and generalization.

Abstract

Item recommendation is a personalized ranking task. To this end, many recommender systems optimize models with pairwise ranking objectives, such as the Bayesian Personalized Ranking (BPR). Using matrix Factorization (MF) --- the most widely used model in recommendation --- as a demonstration, we show that optimizing it with BPR leads to a recommender model that is not robust. In particular, we find that the resultant model is highly vulnerable to adversarial perturbations on its model parameters, which implies the possibly large error in generalization. To enhance the robustness of a recommender model and thus improve its generalization performance, we propose a new optimization framework, namely Adversarial Personalized Ranking (APR). In short, our APR enhances the pairwise ranking method BPR by performing adversarial training. It can be interpreted as playing a minimax game, where the minimization of the BPR objective function meanwhile defends an adversary, which adds adversarial perturbations on model parameters to maximize the BPR objective function. To illustrate how it works, we implement APR on MF by adding adversarial perturbations on the embedding vectors of users and items. Extensive experiments on three public real-world datasets demonstrate the effectiveness of APR --- by optimizing MF with APR, it outperforms BPR with a relative improvement of 11.2% on average and achieves state-of-the-art performance for item recommendation. Our implementation is available at: https://github.com/hexiangnan/adversarial_personalized_ranking.