南京大学学报(自然科学版) ›› 2024, Vol. 60 ›› Issue (1): 12–17.doi: 10.13232/j.cnki.jnju.2024.01.002

• • 上一篇    下一篇

基于用户长短期历史的多兴趣召回算法

张旭, 欧中洪(), 宋美娜   

  1. 北京邮电大学计算机学院,北京,100876
  • 收稿日期:2023-10-27 出版日期:2024-01-30 发布日期:2024-01-29
  • 通讯作者: 欧中洪 E-mail:zhonghong.ou@bupt.edu.cn
  • 基金资助:
    国家自然科学基金(62076035)

Multi⁃interest recall algorithm based on users' long and short⁃term history

Xu Zhang, Zhonghong Ou(), Meina Song   

  1. College of Computer Science,Beijing University of Posts and Telecommunications,Beijing,100876,China
  • Received:2023-10-27 Online:2024-01-30 Published:2024-01-29
  • Contact: Zhonghong Ou E-mail:zhonghong.ou@bupt.edu.cn

摘要:

随着互联网时代的高速发展,用户面临信息过载问题,推荐系统应运而生.推荐系统一般分两个阶段,即推荐召回和推荐排序,推荐召回阶段主要用来筛选出一部分候选集以减小推荐排序阶段的计算压力.多兴趣个性化推荐系统对于每一个用户,算法能学习到用户的多种不同的兴趣偏好,然而目前的多兴趣召回算法只考虑了用户短期历史纪录,忽视了用户长期历史纪录中蕴含的丰富信息.针对这一问题,提出一种基于用户长短期历史的多兴趣召回算法,通过不同的神经网络模型结构分别建模用户长短期兴趣偏好,并通过门控融合网络融合用户长短期兴趣偏好,最终得到用户的多个兴趣偏好,实现了个性化推荐召回.在两个公开数据集上的实验证明了模型的有效性.

关键词: 推荐系统, 序列推荐, 多兴趣, 长短期历史, 图神经网络

Abstract:

With the rapid development of the internet era,users are facing the problem of information overload,and recommendation systems have emerged. Recommendation systems are generally divided into two stages: the recommendation recall stage and the recommendation ranking stage,with the main purpose of the recommendation recall stage being to select a part of the candidate set to reduce the computing load in the recommendation ranking stage. A multi?interest personalized recommendation system learns various users' interest preferences for each user. However,current multi?interest recall algorithms only consider users' short?term history and ignore the rich information contained in users' long?term history. To address this issue,this paper proposes a multi?interest recall algorithm based on users' long and short?term history. The algorithm models users' long and short?term interest preferences through different neural network model structures and uses a gate fusion network to fuse users' long and short?term interest preferences to ultimately obtain users' multiple interest preferences,achieving personalized recommendation recall. The effectiveness of the model is demonstrated through experiments on two public datasets.

Key words: recommendation system, sequential recommendation, multi?interest, long and short?term history, graph neural network

中图分类号: 

  • TP183

图1

LSMNet的整体架构图"

表1

不同召回模型的性能对比"

模型MovieLensTaobao
HR@50NDCG@100HR@100NDCG@100
LSMNet46.3318.2823.719.20
MIND34.4212.9020.687.60
Comirec⁃SA36.7812.4818.697.36
Comirec⁃DR35.5314.1019.957.61
Transformers4Rec41.3416.6418.016.43
SHAN33.9912.3314.554.90
SDM44.3417.8721.848.71

表2

模型各模块的消融实验结果对比"

模型MovieLensTaobao
HR@50NDCG@100HR@100NDCG@100
LSMNet⁃L38.27813.07421.9158.731
LSMNet⁃G44.28817.10522.1168.507
LSMNet46.33418.28023.7089.203
1 岳小琛. 推荐系统中基于模型的协同过滤算法研究. 硕士学位论文.烟台:烟台大学,2022.
Yue X C. Research on model?based collaborative filtering algorithm in recommender system. Master Dissertation. Yantai: YanTai University,2022.
2 Koren Y, Bell R, Volinsky C. Matrix factorization techniques for recommender systems. Computer200942(8):30-37.
3 Koren Y. The bellkor solution to the netflix grand prize. Netflix Prize Documentation2009,81:1-10.
4 虞雅雯,束静,徐影. 基于用户的协同过滤算法对产品评分进行预测研究. 电脑编程技巧与维护2022(5):61-64.
5 吴建帆,曾昭平,郑亮,等. 基于用户的协同过滤推荐算法研究. 现代计算机2020(19):27-29,67.
Wu J F, Zeng S P, Zheng L,et al. Research on user based collaborative filtering recommendation algorithm. Modern Computer2020(19):27-29,67.
6 杨海龙. 基于物品的协同过滤算法的电源推荐系统. 硕士学位论文. 兰州:兰州交通大学,2019.
Yang H L. Movie recommentation system based on collaborative filtering algorithm. Master Dissertation. Lanzhou:Lanzhou Jiaotong University,2019.
7 Liu Z, Lian J C, Yang J H,et al. Octopus:Comprehensive and elastic user representation for the generation of recommendation candidates∥Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Virtual Event:ACM,2020:289-298.
8 Covington P, Adams J, Sargin E. Deep neural networks for youtube recommendations∥Proceedings of the 10th ACM Conference on Recommender Systems. Boston,MA,USA:ACM,2016:191-198.
9 Lu Y J, Zhang S Y, Huang Y X,et al. Future?aware diverse trends framework for recommendation. 2021,arXiv:.
10 Ying H C, Zhuang F Z, Zhang F Z,et al. Sequential recommender system based on hierarchical attention network∥Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm,Sweden:AAAI Press,2018:3926-3932.
11 Yan C R, Wang Y W, Zhang Y T,et al. Modeling long? and short?term user behaviors for sequential recommendation with deep neural networks∥2021 International Joint Conference on Neural Networks. Shenzhen,China:IEEE,2021:1-8.
12 Zhu H, Li X, Zhang P Y,et al. Learning tree?based deep model for recommender systems∥Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. London,United Kingdom:ACM,2018:1079-1088.
13 Lv F, Jin T, Yu C,et al. SDM:Sequential deep matching model for online large?scale recommender system∥Proceedings of the 28th ACM International Conference on Information and Knowledge Manage?ment. Beijing,China:ACM,2019:2635-2643.
14 Cen Y K, Zhang J W, Zou X,et al. Controllable multi?interest framework for recommendation∥Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Virtual Event:ACM,2020:2942-2951.
15 Li C, Liu Z Y, Wu M M,et al. Multi?interest network with dynamic routing for recommendation at Tmall∥Proceedings of the 28th ACM International Conference on Information and Knowledge Manage?ment. Beijing,China:ACM,2019:2615-2623.
16 de Souza Pereira Moreira G, Rabhi S, Lee J M,et al. Transformers4Rec:Bridging the gap between NLP and sequential/session?based recommendation∥Proceedings of the 15th ACM Conference on Recommender Systems. Amsterdam,Netherlands:ACM,2021:143-153.
17 Abadi M, Barham P, Chen J M,et al. TensorFlow:A system for large?scale machine learning∥Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation. Savannah,GA,USA:USENIX Association,2016:265-283.
18 Kingma D P, Ba J. Adam:A method for stochastic optimization. 2017,arXiv:.
[1] 钱峰, 张蕾, 赵姝, 陈洁. 利用粗图训练图神经网络实现网络对齐[J]. 南京大学学报(自然科学版), 2023, 59(6): 947-960.
[2] 武桐舟, 刘强, 王亮. 基于不确定性估计的推荐系统多任务学习去偏方法[J]. 南京大学学报(自然科学版), 2023, 59(4): 543-549.
[3] 刘志中, 李林霞, 孟令强. 基于混合图神经网络的个性化POI推荐方法研究[J]. 南京大学学报(自然科学版), 2023, 59(3): 373-387.
[4] 张蕾, 钱峰, 赵姝, 陈洁, 杨雪洁, 张燕平. 基于卷积图神经网络的多粒度表示学习框架[J]. 南京大学学报(自然科学版), 2023, 59(1): 43-54.
[5] 韩迪, 陈怡君, 廖凯, 林坤玲. 推荐系统中的准确性、新颖性和多样性的有效耦合与应用[J]. 南京大学学报(自然科学版), 2022, 58(4): 604-614.
[6] 王扬, 陈智斌, 杨笑笑, 吴兆蕊. 深度强化学习结合图注意力模型求解TSP问题[J]. 南京大学学报(自然科学版), 2022, 58(3): 420-429.
[7] 吕亚兰, 徐媛媛, 张恒汝. 一种可解释性泛化矩阵分解推荐算法[J]. 南京大学学报(自然科学版), 2022, 58(1): 135-142.
[8] 武聪, 马文明, 王冰, 朱建豪. 融合用户标签相似度的矩阵分解算法[J]. 南京大学学报(自然科学版), 2022, 58(1): 143-152.
[9] 郝昱猛, 马文明, 王冰. 基于特定用户约束的概率矩阵分解算法[J]. 南京大学学报(自然科学版), 2021, 57(5): 818-827.
[10] 徐樱笑, 资文杰, 宋洁琼, 邵瑞喆, 陈浩. 基于多站点、多时间注意力机制的电磁强度时空关联分析与可视化[J]. 南京大学学报(自然科学版), 2021, 57(5): 838-846.
[11] 袁晓峰, 钱苏斌, 周彩根. 基于填充先验约束的矩阵分解算法[J]. 南京大学学报(自然科学版), 2021, 57(2): 197-207.
[12] 徐媛媛,张恒汝,闵帆,黄雨婷. 三支交互推荐[J]. 南京大学学报(自然科学版), 2019, 55(6): 973-983.
[13] 何轶凡, 邹海涛, 于化龙. 基于动态加权Bagging矩阵分解的推荐系统模型[J]. 南京大学学报(自然科学版), 2019, 55(4): 644-650.
[14] 张燕平1,2张顺1,2钱付兰1,2严远亭1,2. 一种局部和全局用户影响力相结合的社交推荐算法[J]. 南京大学学报(自然科学版), 2015, 51(4): 858-865.
[15]  韦素云1**,业宁1,吉根林2,张丹丹1,殷晓飞1
.  基于项目类别和兴趣度的协同过滤推荐算法*[J]. 南京大学学报(自然科学版), 2013, 49(2): 142-149.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!