ABSTRACT
Recommender systems (RSs) employ user-item feedback, e.g., ratings, to match customers to personalized lists of products. Approaches to top-k recommendation mainly rely on Learning-To-Rank algorithms and, among them, the most widely adopted is Bayesian Personalized Ranking (BPR), which bases on a pair-wise optimization approach. Recently, BPR has been found vulnerable against adversarial perturbations of its model parameters. Adversarial Personalized Ranking (APR) mitigates this issue by robustifying BPR via an adversarial training procedure. The empirical improvements of APR's accuracy performance on BPR have led to its wide use in several recommender models. However, a key overlooked aspect has been the beyond-accuracy performance of APR, i.e., novelty, coverage, and amplification of popularity bias, considering that recent results suggest that BPR, the building block of APR, is sensitive to the intensification of biases and reduction of recommendation novelty. In this work, we model the learning characteristics of the BPR and APR optimization frameworks to give mathematical evidence that, when the feedback data have a tailed distribution, APR amplifies the popularity bias more than BPR due to an unbalanced number of received positive updates from short-head items. Using matrix factorization (MF), we empirically validate the theoretical results by performing preliminary experiments on two public datasets to compare BPR-MF and APR-MF performance on accuracy and beyond-accuracy metrics. The experimental results consistently show the degradation of novelty and coverage measures and a worrying amplification of bias.
- Himan Abdollahpouri, Robin Burke, and Bamshad Mobasher. 2017. Controlling Popularity Bias in Learning-to-Rank Recommendation. In RecSys. ACM, 42--46. Google ScholarDigital Library
- Himan Abdollahpouri, Robin Burke, and Bamshad Mobasher. 2019. Managing Popularity Bias in Recommender Systems with Personalized Re-Ranking. In FLAIRS Conference. AAAI Press, 413--418.Google Scholar
- Vito Walter Anelli, Alejandro Bellogín, Yashar Deldjoo, Tommaso Di Noia, and Felice Antonio Merra. 2021 a. MSAP: Multi-Step Adversarial Perturbations on Recommender Systems Embeddings. In The International FLAIRS Conference Proceedings (FLAIRS 2021), Vol. 34. https://doi.org/10.32473/flairs.v34i1.128443Google Scholar
- Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Daniele Malitesta, and Felice Antonio Merra. 2021 c. A Study of Defensive Methods to Protect Visual Recommendation Against Adversarial Manipulation of Images. In SIGIR 2021. ACM.Google ScholarDigital Library
- Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, and Felice Antonio Merra. 2021 b. Adversarial Recommender Systems: Attack, Defense, and Advances. the Third Edition of Recommender Systems Handbook, Springer.Google Scholar
- Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Antonio Ferrara, and Fedelucio Narducci. 2021 d. FedeRank: User Controlled Feedback with Federated Recommender Systems. In ECIR (1) (Lecture Notes in Computer Science, Vol. 12656). Springer, 32--47.Google Scholar
- Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Eugenio Di Sciascio, and Felice Antonio Merra. 2020. SAShA: Semantic-Aware Shilling Attacks on Recommender Systems Exploiting Knowledge Graphs. In The Semantic Web - 17th International Conference, ESWC 2020, Heraklion, Crete, Greece, May 31-June 4, 2020, Proceedings. 307--323. https://doi.org/10.1007/978-3-030-49461-2_18Google Scholar
- Ludovico Boratto, Gianni Fenu, and Mirko Marras. 2021. Connecting user and item perspectives in popularity debiasing for collaborative recommendation. Inf. Process. Manag., Vol. 58, 1 (2021), 102387.Google ScholarCross Ref
- Huiyuan Chen and Jing Li. 2019. Adversarial tensor factorization for context-aware recommendation. In RecSys. ACM, 363--367. Google ScholarDigital Library
- Jingyuan Chen, Hanwang Zhang, Xiangnan He, Liqiang Nie, Wei Liu, and Tat-Seng Chua. 2017. Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention. In SIGIR. ACM, 335--344. Google ScholarDigital Library
- Rami Cohen, Oren Sar Shalom, Dietmar Jannach, and Amihood Amir. 2021. A Black-Box Attack Model for Visually-Aware Recommender Systems. In WSDM. ACM, 94--102. Google ScholarDigital Library
- Quanyu Dai, Xiao Shen, Liang Zhang, Qiang Li, and Dan Wang. 2019. Adversarial Training Methods for Network Embedding. In WWW. ACM, 329--339. Google ScholarDigital Library
- Yashar Deldjoo, Tommaso Di Noia, Daniele Malitesta, and Felice Antonio Merra. 2021 b. A Study on the Relative Importance of Convolutional Neural Networks in Visually-Aware Recommender Systems. In CVPR Workshops. 3961--3967.Google ScholarCross Ref
- Yashar Deldjoo, Tommaso Di Noia, and Felice Antonio Merra. 2021 a. A survey on adversarial recommender systems: from attack/defense strategies to generative adversarial networks. Comput. Surveys, Vol. 54, 2 (2021), 1--38. Google ScholarDigital Library
- Yashar Deldjoo, Tommaso Di Noia, Eugenio Di Sciascio, and Felice Antonio Merra. 2020. How Dataset Characteristics Affect the Robustness of Collaborative Recommendation Models. In SIGIR. ACM, 951--960. Google ScholarDigital Library
- F. Feng, X. He, J. Tang, and T. Chua. 2019. Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure. IEEE Transactions on Knowledge and Data Engineering (2019), 1--1. https://doi.org/10.1109/TKDE.2019.2957786Google Scholar
- Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In ICLR (Poster).Google Scholar
- F. Maxwell Harper and Joseph A. Konstan. 2016. The MovieLens Datasets: History and Context. ACM Trans. Interact. Intell. Syst., Vol. 5, 4 (2016), 19:1--19:19. Google ScholarDigital Library
- Xiangnan He, Zhankui He, Xiaoyu Du, and Tat-Seng Chua. 2018. Adversarial Personalized Ranking for Recommendation. In SIGIR. ACM, 355--364. Google ScholarDigital Library
- Balá zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2016. Session-based Recommendations with Recurrent Neural Networks. In ICLR (Poster).Google Scholar
- Dietmar Jannach, Lukas Lerche, Iman Kamehkhosh, and Michael Jugovac. 2015. What recommenders recommend: an analysis of recommendation biases and possible countermeasures. User Model. User Adapt. Interact., Vol. 25, 5 (2015), 427--491. Google ScholarDigital Library
- Yehuda Koren, Robert M. Bell, and Chris Volinsky. 2009. Matrix Factorization Techniques for Recommender Systems. IEEE Computer, Vol. 42, 8 (2009), 30--37. Google ScholarDigital Library
- Ruirui Li, Xian Wu, and Wei Wang. 2020. Adversarial Learning to Compare: Self-Attentive Prospective Customer Recommendation in Location based Social Networks. In WSDM. ACM, 349--357. Google ScholarDigital Library
- D. Liu, Y. Sun, X. Zhao, G. Zhang, and R. Liu. 2020. Adversarial Training for Session-based Item Recommendations. In 2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), Vol. 9. 1162--1168. https://doi.org/10.1109/ITAIC49862.2020.9338819Google Scholar
- Zhuoran Liu and Martha A. Larson. 2021. Adversarial Item Promotion: Vulnerabilities at the Core of Top-N Recommenders that Use Images to Address Cold Start. In WWW. ACM / IW3C2, 3590--3602. Google ScholarDigital Library
- Masoud Mansoury, Himan Abdollahpouri, Mykola Pechenizkiy, Bamshad Mobasher, and Robin Burke. 2020. Feedback Loop and Bias Amplification in Recommender Systems. In CIKM. ACM, 2145--2148. Google ScholarDigital Library
- Julian J. McAuley, Christopher Targett, Qinfeng Shi, and Anton van den Hengel. 2015. Image-Based Recommendations on Styles and Substitutes. In SIGIR. ACM, 43--52. Google ScholarDigital Library
- Xia Ning, Christian Desrosiers, and George Karypis. 2015. A Comprehensive Survey of Neighborhood-Based Recommendation Methods. In Recommender Systems Handbook. Springer, 37--76.Google Scholar
- Tommaso Di Noia, Daniele Malitesta, and Felice Antonio Merra. 2020. TAaMR: Targeted Adversarial Attack against Multimedia Recommender Systems. In 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops, DSN Workshops 2020, Valencia, Spain, June 29 - July 2, 2020. 1--8. https://doi.org/10.1109/DSN-W50199.2020.00011Google Scholar
- Dae Hoon Park and Yi Chang. 2019. Adversarial Sampling and Training for Semi-Supervised Information Retrieval. In WWW. ACM, 1443--1453. Google ScholarDigital Library
- Steffen Rendle and Christoph Freudenthaler. 2014. Improving pairwise learning for item recommendation from implicit feedback. In WSDM. ACM, 273--282. Google ScholarDigital Library
- Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian Personalized Ranking from Implicit Feedback. In UAI. AUAI Press, 452--461. Google ScholarDigital Library
- Jinhui Tang, Xiaoyu Du, Xiangnan He, Fajie Yuan, Qi Tian, and Tat-Seng Chua. 2020. Adversarial Training Towards Robust Multimedia Recommender System. IEEE Trans. Knowl. Data Eng., Vol. 32, 5 (2020), 855--867.Google ScholarCross Ref
- Thanh Tran, Renee Sweeney, and Kyumin Lee. 2019. Adversarial Mahalanobis Distance-based Attentive Song Recommender for Automatic Playlist Continuation. In SIGIR. ACM, 245--254. Google ScholarDigital Library
- Jianfang Wang, Zhiyuan Fu, Mingxin Niu, Pengbo Zhang, and Qiuling Zhang. 2020. Multi-feedback Pairwise Ranking via Adversarial Training for Recommender. Chinese Journal of Electronics, Vol. 29, 4 (2020), 615--622. https://doi.org/10.1049/cje.2020.05.004Google ScholarCross Ref
- Jianfang Wang and Pengfei Han. 2020. Adversarial Training-Based Mean Bayesian Personalized Ranking for Recommender System. IEEE Access, Vol. 8 (2020), 7958--7968.Google ScholarCross Ref
- Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. 2019. Neural Graph Collaborative Filtering. In SIGIR. ACM, 165--174. Google ScholarDigital Library
- Hu Weibo, Chen Chuan, Chang Yaomin, Zheng Zibin, and Du Yunfei. 2021. Robust graph convolutional networks with directional graph adversarial training. Applied Intelligence (2021).Google Scholar
- Feng Yuan, Lina Yao, and Boualem Benatallah. 2019 a. Adversarial Collaborative Auto-encoder for Top-N Recommendation. In IJCNN. IEEE, 1--8.Google Scholar
- Feng Yuan, Lina Yao, and Boualem Benatallah. 2019 b. Adversarial Collaborative Neural Network for Robust Recommendation. In SIGIR. ACM, 1065--1068. Google ScholarDigital Library
- Feng Yuan, Lina Yao, and Boualem Benatallah. 2020. Exploring Missing Interactions: A Convolutional Generative Adversarial Network for Collaborative Filtering. In CIKM. ACM, 1773--1782. Google ScholarDigital Library
- Tao Zhou, Zoltán Kuscsik, Jian-Guo Liu, Matúv s Medo, Joseph Rushton Wakeling, and Yi-Cheng Zhang. 2010. Solving the apparent diversity-accuracy dilemma of recommender systems. Proceedings of the National Academy of Sciences, Vol. 107, 10 (2010), 4511--4515. https://doi.org/10.1073/pnas.1000488107Google ScholarCross Ref
- Ziwei Zhu, Jianling Wang, and James Caverlee. 2020. Measuring and Mitigating Item Under-Recommendation Bias in Personalized Ranking Systems. In SIGIR. ACM, 449--458. Google ScholarDigital Library
Index Terms
- A Formal Analysis of Recommendation Quality of Adversarially-trained Recommenders
Recommendations
What recommenders recommend: an analysis of recommendation biases and possible countermeasures
Most real-world recommender systems are deployed in a commercial context or designed to represent a value-adding service, e.g., on shopping or Social Web platforms, and typical success indicators for such systems include conversion rates, customer ...
Improving Collaborative Filtering Based Recommenders Using Topic Modelling
WI-IAT '14: Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) - Volume 01Standard Collaborative Filtering (CF) algorithms make use of interactions between users and items in the form of implicit or explicit ratings alone for generating recommendations. Similarity among users or items is calculated purely based on rating ...
New Recommendation Techniques for Multicriteria Rating Systems
Traditional single-rating recommender systems have been successful in a number of personalization applications, but the research area of multicriteria recommender systems has been largely untouched. Taking full advantage of multicriteria ratings in ...
Comments