Adversarial Personalized Ranking for Recommendation

08/12/2018
by   Xiangnan He, et al.
0

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 state-of-the-art performance for item recommendation. Our implementation is available at: https://github.com/hexiangnan/adversarial_personalized_ranking.

READ FULL TEXT
research
07/29/2021

Understanding the Effects of Adversarial Personalized Ranking Optimization Method on Recommendation Quality

Recommender systems (RSs) employ user-item feedback, e.g., ratings, to m...
research
10/03/2020

Multi-Step Adversarial Perturbations on Recommender Systems Embeddings

Recommender systems (RSs) have attained exceptional performance in learn...
research
09/19/2018

Adversarial Training Towards Robust Multimedia Recommender System

With the prevalence of multimedia content on the Web, developing recomme...
research
08/20/2019

Hierarchical Bayesian Personalized Recommendation: A Case Study and Beyond

Items in modern recommender systems are often organized in hierarchical ...
research
10/14/2019

iSplit LBI: Individualized Partial Ranking with Ties via Split LBI

Due to the inherent uncertainty of data, the problem of predicting parti...
research
02/09/2023

Adap-τ: Adaptively Modulating Embedding Magnitude for Recommendation

Recent years have witnessed the great successes of embedding-based metho...
research
04/26/2022

Cross Pairwise Ranking for Unbiased Item Recommendation

Most recommender systems optimize the model on observed interaction data...

Please sign up or login with your details

Forgot password? Click here to reset