Adversarial Personalized Ranking for Recommendation

By Xiangnan He, Zhankui He, Xiaoyu Du, Tat-seng Chua. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2018

434 citations recorded by the source corpus.

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: \urlhttps://github.com/hexiangnan/adversarial_personalized_ranking.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/97cefa2f54d30bf40b2bf71a9297949ed5a327ee

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Information Systems

In Management Science and Operations Research

Citations in the corpus

Deep Learning Based Recommender System (2017, methodology): “[52] proposed an adversarial personalized ranking approach which enhances the Bayesian personalized ranking with adversarial training.”
Outer Product-based Neural Collaborative Filtering (2018, methodology): “…2017] extends MF by learning embeddings with deep neural networks, BPR [Rendle et al., 2009] learns MF from implicit feedback with a pairwise ranking objective, and the recently proposed adversarial personalized ranking (APR) [He et al., 2018] employs an adversarial training procedure to learn MF.”
Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences (2019, methodology): “With the surge of neural network (NN) models, a host of methods extend similarity-based methods with NN and present a more effective mechanism in automatically extracting latent features of users and items for recommendation [7, 12–14].”
Diffusion Recommender Model (2023, methodology): “GAN-based approaches utilize adversarial training [9, 41, 45, 49] to optimize the generator for predicting user interactions [3, 6, 15].”
NAIS: Neural Attentive Item Similarity Model for Recommendation (2018, background): “A state-of-the-art work develops adversarial personalized ranking [37], which employs adver-”
A Simple Convolutional Generative Network for Next Item Recommendation (2018, methodology): “We reported the evaluated results by three popular top-N metrics, namely MRR@ N (Mean Reciprocal Rank) [15], HR@ N (Hit Ratio) [13] and NDCG@ N [34] (Normalized Discounted Cumulative Gain).”
Cross-domain Recommendation Without Sharing User-relevant Data (2019, neutral): “Following existing works [12, 31], we employ the widely used leave-one-out evaluation protocol in the evaluation stage.”
Graph Neural Networks in Recommender Systems: A Survey (2020, background): “In the field of GNN, there are emerging efforts on graph adversarial learning to enhance the robustness [55, 186, 210].”
λOpt: Learn to Regularize Recommender Models in Finer Levels (2019, neutral): “- AMF [15].”
Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation (2021, methodology): “Adversarial learning has been successfully utilized in some models like APR [4].”
Recommendation system based on deep learning methods: a systematic review and new directions (2019, methodology): “He et al. (2018) introduced an adversarial personalized ranking method which uses adversarial training for improving the Bayesian personalized ranking.”
Neural Graph Collaborative Filtering (2019, methodology): “Moreover, we are interested in exploring the adversarial learning [13] on user/item embedding and the graph”
Adversarial Distillation for Efficient Recommendation with External Knowledge (2018, background): “[11] designed adversarial personalized ranking (APR) to enhance the robustness of a recommender model for improving its generalization performance.”
MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video (2019, methodology): “Due to the success of CF method in recommendation systems, early multi-modal recommendation algorithms mainly based on CF models [6, 18, 38–40].”