Multi-feedback Pairwise Ranking via Adversarial Training for Recommender

WANG Jianfang; FU Zhiyuan; NIU Mingxin; ZHANG Pengbo; ZHANG Qiuling

doi:10.1049/cje.2020.05.004

Volume 29 Issue 4

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2020 > 29(4): 615-622

WANG Jianfang, FU Zhiyuan, NIU Mingxin, et al., “Multi-feedback Pairwise Ranking via Adversarial Training for Recommender,” Chinese Journal of Electronics, vol. 29, no. 4, pp. 615-622, 2020, doi: 10.1049/cje.2020.05.004

Citation:

WANG Jianfang, FU Zhiyuan, NIU Mingxin, et al., “Multi-feedback Pairwise Ranking via Adversarial Training for Recommender,” Chinese Journal of Electronics, vol. 29, no. 4, pp. 615-622, 2020, doi: 10.1049/cje.2020.05.004

Citation:

PDF( 1397 KB)

Multi-feedback Pairwise Ranking via Adversarial Training for Recommender

doi: 10.1049/cje.2020.05.004

College of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454003, China

Received Date: 2019-10-24
Rev Recd Date: 2020-03-16
Publish Date: 2020-07-10

Abstract

Abstract

Personalized recommendation systems predict potential demand by analyzing user preferences. Generally, user feedback information is inferred from implicit feedback or explicit feedback. Nevertheless, feedback can be contaminated by user's mis-operations or malicious operations, and may thus lead to incorrect results. We propose a novel Multi-feedback pairwise ranking method via Adversarial training (AT-MPR) for recommender to enhance the robustness and overall performance in the event of rating pollution. The MPR method extends Bayesian personalized ranking (BPR) to cover three types of feedback: positive, negative, and unobserved. It obtains user preferences in a probabilistic way through multiple feedbacks at different levels. To reduce the impact of feedback noise, we train an MPR objective function using minimax adversarial training. Experiments on two datasets show that the AT-MPR model achieves satisfactory performance and outperforms the state-of-the-art implicit feedback collaborative ranking models in two evaluation metrics.
- Adversarial training,
- Pairwise ranking,
- Collaborative filtering,
- Recommender system

FullText(HTML)

References(24)

References

L. Hu, J. Cao, G. Xu, et al., “Personalized recommendation via cross domain triadic factorization”, Proc. of International Conference on World Wide Web, New York, United States, USA, pp.595-606, 2013.

M. Deshpande and G. Karypis, “Item-based top-N recommendation algorithms”, ACM Transactions on Information Systems, Vol.22, No.1, pp.143-177, 2004.

Y. Koren, “Factorization meets the neighborhood: A multifaceted collaborative filtering model”, Proc. of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, USA, pp.426-434, 2008.

R. Pan, Y. Zhou, B. Cao, et al., “One-class collaborative filtering”, Proc. of IEEE International Conference on Data Mining, Pisa, Italy, pp.502-511, 2008.

Z. Cao, “Learning to rank: From pairwise approach to listwise approach”, Proc. of Machine learning, Corvalis, Oregon, USA, pp.129-136, 2007.

S. Rendle, C. Freudenthaler, Z. Gantner, et al., “Bayesian personalized ranking from implicit feedback”, Proc. of Uncertainty in Artificial Intelligence, Montreal, Quebec, Canada, pp.452-461, 2009.

Y. Runlong, Z. Yunzhou, Y. Yuyang, et al., “Multiple pairwise ranking with implicit feedback”, Proc. of ACM International Conference on Information and Knowledge Management, Lingotto, Turin, Italy, pp.1727-1730, 2018.

X. N. He, Z. K. He, X. Y. Du, et al., “Adversarial personalized ranking for recommendation”, Proc. of SIGIR, Ann Arbor, Michigan, USA, pp.355-364, 2018.

YU Dong-jin, CHEN Cong, WU Jian-hua, et al., “Personalized game recommendation based on implicit feedback”, Chinese Journal of Electronics, Vol.27, No.4, pp.2626-2632, 2018.

T. Y. Liu, “Learning to rank for information retrieval”, Found Trends INF. RET., Vol.3, No.3, pp.225-331, 2009.

T. Zhao, J. McAuley and I. King, “Leveraging social connections to improve personalized ranking for collaborative filtering”, Proc. of ACM International Conference on Information and Knowledge Management, Shanghai, China, pp.261-270, 2014.

J. L. Peugh and C. K. Enders, “Missing data in educational research: A review of reporting practices and suggestions for improvement”, Review of Educational Research, Vol.74, No.4, pp.525-556, 2004.

X. He, H. Zhang, M. Y. Kan, et al., “Fast matrix factorization for online recommendation with implicit feedback”, Proc. of SIGIR, Pisa, Tuscany, Italy, pp.549-558, 2016.

R. Loftin, B. Peng, J. MacGlashan, et al., “Learning behaviors via human-delivered discrete feedback: Modeling implicit feedback strategies to speed up learning”, Auton. Agent. Multi-Ag., Vol.30, No.1, pp.30-59, 2016.

X. Chen, P. F. Wang, Z. Qin, et al., “Hlbpr: A hybrid local bayesian personal ranking method”, Proc. of International Conference on World Wide Web, Montreal, Canada, pp.21-22, 2016.

L. Babak, P. Roberto, L. Martha, et al., “Bayesian personalized ranking with multi-channel user feedback”, Proc. of RecSys, Boston, USA, pp.361-364, 2016.

J. W. Li, W. Monroe, T. L. Shi, et al., “Adversarial learning for neural dialogue generation”, Proc. of EMNLP, Copenhagen, Denmark, pp.2147-2159, 2017.

FANG Chen， ZHANG Heng-wei， WANG Na, et al., “Personalized service recommendation method based on andom walk and diversified graph Ranking”, Chinese Journal of Electronics, Vol.27, No.4, pp.89-96, 2018.

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, et al., “Generative adversarial nets”, Proc. of NIPS, Montreal, Quebec, Canada, pp.2672-2680, 2014.

F. Yuan, L. N. Yao and B. Benatallah, “Adversarial collaborative neural network for robust recommendation”, Proc. of SIGIR, Paris, France, pp.21-25, 2019.

LI Shuang, YAN Yanghui, REN Ju, et al., “A sample-efficient actor-critic algorithm for recommendation diversification”, Chinese Journal of Electronics, Vol.29, No.1, pp.89-96, 2020.

H. Xiangnan, L. Lizi, Z. Hanwang, et al., “Neural Collaborative Filtering”, Proc. of International Conference on World Wide Web, Perth, Australia, pp.173-182, 2017.

Y. F. Zhang, ”Joint representation learning for top-n recommendation with heterogeneous information sources”, Proc. of ACM CIKM, Singapore, pp.1449-1458, 2017.

W. Yao, D. B. Christopher, X. Z. Alice, et al., “Collaborative Denoising Auto-Encoders for Top-N Recommender Systems”, Proc. of ACM International Conference on Web Search and Data Mining, San Francisco, California, USA, pp.153-162, 2016.

Relative Articles

Supplements(0)

Cited By

Proportional views