带有均匀性约束和重要性均衡的基于原型的推荐方法

doi:10.6040/j.issn.1671-9352.2.2024.089

摘要/Abstract

摘要： 基于原型的推荐算法可以通过学习一组代表典型偏好或共性特点的用户原型(或物品原型)表示,以及用户(或物品)与原型之间的关联强度,实现可解释的推荐。然而,现有算法忽视了原型表示之间的差异性以及不同原型之间的负载均衡,不能充分释放模型的表达能力。因此,以ProtoMF为基础,提出一种带有均匀性约束和重要性均衡的基于原型的推荐方法ProtoMF++。该方法在用户原型(或物品原型)之间添加均匀性约束,通过最小化原型表示之间的平均成对高斯势的对数,提升原型表示之间的差异性;另外,将每个原型与所有用户(或物品)的累计关联强度视作其负载重要性,通过最小化各个原型的负载重要性的变异系数,实现不同原型之间的重要性均衡。在3个基准数据集上进行实验,结果表明ProtoMF++的推荐效果优于现有基于原型的推荐方法,在Baby数据集上,HitRatio@10和NDCG@10指标值分别提升4.74%和10.64%。

关键词: 推荐系统, 原型表示, 均匀性约束, 重要性均衡

Abstract: Prototype-based recommendation algorithms can achieve explainable recommendations by learning a set of user prototypes(or item prototypes)that represent typical preferences or common characteristics, as well as the association strength between users(or items)and prototypes. However, existing algorithms overlook the differences between prototypes and the load balancing among them, and hence cannot fully release the expressive power of the model. Therefore, a prototype-based recommendation method ProtoMF++ with uniformity constraints and importance balancing is developed on top of ProtoMF. This method added uniformity constraints between user prototypes(or item prototypes)and enhanced the differences between prototypes by minimizing the logarithm of the average pairwise Gaussian potential between prototype representations. In addition, the load importance of each prototype is defined as the total association strength between it and all users(or items), and the coefficient of variation of their load importance is minimized to realize importance balancing across different prototypes. Experiments are conducted on three benchmark datasets, and the results show that ProtoMF++ outperforms existing prototype-based recommendation methods. For example, on the Baby dataset, the values of HitRatio@10 and NDCG@10 increase by 4.74% and 10.64%, respectively.

Key words: recommender system, prototype representation, uniformity constraint, importance balancing

中图分类号:

TP391

曹玉祥,廉涛,王龙,荆星博,窦浩铖. 带有均匀性约束和重要性均衡的基于原型的推荐方法[J]. 《山东大学学报(理学版)》, 2026, 61(3): 75-85.

CAO Yuxiang, LIAN Tao, WANG Long, JING Xingbo, DOU Haocheng. Prototype-based recommendation method with uniformity constraints and importance balancing[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2026, 61(3): 75-85.

参考文献

[1] ABDOLLAHI B, NASRAOUI O. Explainable matrix factorization for collaborative filtering[C] //Proceedings of the 25th International Conference Companion on World Wide Web. Montréal: ACM, 2016:5-6.
[2] HASE P, CHEN CF, LI O, et al. Interpretable image recognition with hierarchical prototypes[C] //Proceedings of the AAAI Conference on Human Computation & Crowdsourcing. Skamania Lodge: AAAI Press, 2019:32-40.
[3] LI O, LIU H, CHEN C F, et al. Deep learning for case-based reasoning through prototypes: a neural network that explains its predictions[C] //Proceedings of the AAAI Conference on Artificial Intelligence. New Orleans: AAAI Press, 2018:3530-3537.
[4] MELCHIORRE A B, REKABSAZ N, GANHÖR C, et al. ProtoMF: prototype-based matrix factorization for effective and explainable recommendations[C] //Proceedings of 16th ACM Conference on Recommender Systems. Seattle: ACM, 2022:246-256.
[5] MAO Kelong, ZHU Jieming, WANG Jinpeng, et al. SimpleX: a simple and strong baseline for collaborative filtering[C] //Proceedings of the 30th ACM International Conference on Information & Knowledge Management. New York: ACM, 2021:1243-1252.
[6] RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR: Bayesian personalized ranking from implicit feedback[C] //Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. Montreal: AUAI Press, 2009:452-461.
[7] ZHOU Chang, MA Jianxin, ZHANG Jianwei, et al. Contrastive learning for debiased candidate generation in large-scale recommender systems[C] //Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. New York: ACM, 2021:3985-3995.
[8] PARK S, YOON M, LEE J, et al. Toward a better understanding of loss functions for collaborative filtering[C] //Proceedings of the 32nd ACM International Conference on Information & Knowledge Management. Birmingham: ACM, 2023:2034-2043.
[9] WANG Chenyang, YU Yuanqing, MA Weizhi, et al. Towards representation alignment and uniformity in collaborative filtering[C] //Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. Washington: ACM, 2022:1816-1825.
[10] SHAZEER N, MIRHOSEINI A, MAZIARZ K, et al. Outrageously large neural networks: the sparsely-gated mixture-of-experts layer[C] //International Conference on Learning Representations. Toulon: OpenReview, 2017.
[11] SAGTANI H, JHAWAR M G, MEHROTRA R, et al. Ad-load balancing via off-policy learning in a content marketplace[C] //Proceedings of the 17th ACM International Conference on Web Search & Data Mining. Merida: ACM, 2024:586-595.
[12] LIU N, MENG X R, LIU C, et al. Wisdom of the better few: cold start recommendation via representative based rating elicitation[C] //Proceedings of the 5th ACM conference on Recommender systems. Chicago: ACM, 2011:37-44.
[13] BARKAN O, HIRSCH R, KATZ O, et al. Anchor-based collaborative filtering[C] //Proceedings of the 30th ACM International Conference on Information & Knowledge Management. New York: ACM, 2021:2877-2881.
[14] DU Yuntao, LIAN Jianxun, YAO Jing, et al. Towards explainable collaborative filtering with taste clusters learning[C] //Proceedings of the ACM Web Conference 2023. Austin: ACM, 2023:3712-3722.
[15] WANG T Z, ISOLA P. Understanding contrastive representation learning through alignment and uniformity on the hypersphere[C/OL] //Proceedings of the 37th International Conference on Machine Learning, 2020:9929-9939. http://proceedings.mlr.press/v119/wang20k/wang20k.pdf.
[16] YAN Rong, BAO Peng, ZHANG Xiao, et al. Towards alignment-uniformity aware representation in graph contrastive learning[C] //Proceedings of the 17th ACM International Conference on Web Search & Data Mining. Merida: ACM, 2024:873-881.
[17] JEAN S, CHO K, MEMISEVIC R, et al. On using very large target vocabulary for neural machine translation[C] //Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Beijing: ACL, 2015:1-10.
[18] MCAULEY J, TARGETT C, SHI J, et al. Image-based recommendations on styles and substitutes[C] //Proceedings of the 38th International ACM SIGIR Conference on Research & Development in Information Retrieval. Santiago: ACM, 2015:43-52.
[19] CREMONESI P, TURRIN R, LENTINI E, et al. An evaluation methodology for collaborative recommender systems[C] //2008 International Conference on Automated Solutions for Cross Media Content & Multi-Channel Distribution. Florence: IEEE, 2008:224-231.
[20] KINGMA D P, BA J L. Adam: a method for stochastic optimization[EB/OL].(2015-07-23)[2024-10-09].https://arxiv.org/abs/1412.6980.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed