基于双编码器的会话型推荐模型

方军; 管业鹏

doi:10.7652/xjtuxb202108020

您当前的位置：

首页 >

文章列表页 >

基于双编码器的会话型推荐模型

更新时间：2025-07-09

- 基于双编码器的会话型推荐模型
- A Session Recommendation Model Based on Dual Encoders
- 西安交通大学学报 2021年55卷第8期页码：166-174
- 作者机构：
  
  上海大学通信与信息工程学院,上海,200444
- 作者简介：
- 基金信息：
  
  : 2020-12-22。作者简介: 方军(1989—),男,硕士生;管业鹏(通信作者),男,教授,博士生导师。基金项目: 国家重点研发计划资助项目(2019YCF1520500,2020YFC1523004)
- DOI：10.7652/xjtuxb202108020
  中图分类号： TP391.3
- 网络首发：2021-08-10，
  
  纸质出版：2021
- 稿件说明：
移动端阅览
方军, 管业鹏. 基于双编码器的会话型推荐模型[J]. 西安交通大学学报, 2021,55(8):166-174.

A Session Recommendation Model Based on Dual Encoders[J]. 2021, 55(8): 166-174.
方军, 管业鹏. 基于双编码器的会话型推荐模型[J]. 西安交通大学学报, 2021,55(8):166-174. DOI： 10.7652/xjtuxb202108020.

A Session Recommendation Model Based on Dual Encoders[J]. 2021, 55(8): 166-174. DOI： 10.7652/xjtuxb202108020.

摘要

针对现有会话型推荐模型难以准确捕获物品间全局依赖的问题

提出了一种基于双编码器的会话型推荐模型(SR-BE)。该双编码器由基于自注意力网络的全局编码器和基于图神经网络的局部编码器组成

无论被浏览物品之间的时间间隔长还是短

全局编码器都能够利用注意力机制自适应地捕获被浏览物品之间的全局依赖

并将其编码为全局隐向量。为弥补自注意力网络没有结构信息而难以捕获邻近物品间局部依赖的不足

在局部编码器中

首先将会话序列构建成会话图

然后通过图神经网络在会话图上捕获邻近物品间的局部依赖

并将其编码为局部隐向量。最后将从双编码器得到的全局隐向量和局部隐向量线性组合为会话表示

再通过预测层解码会话表示得到每个候选物品被点击的概率。实验结果表明:将基于自注意力网络的全局编码器与基于图神经网络的局部编码器结合在一起

比单一地使用全局编码器或局部编码器在命中率上分别提高了3.11%和6.55%。通过与同类模型客观定量比较

SR-BE模型在两个公开数据集上取得了突出的效果

表明该模型有效、可行。

Abstract

A session recommendation model based on dual encoders(SR-BE)is proposed to solve the problem that it is difficult to accurately capture the global dependencies between items in the existing session recommendation models. The dual encoder consists of a global encoder based on self-attention network and a local encoder based on graph neural network. The global encoder can adaptively capture the global dependencies among all items by using the attention mechanism regardless of their time intervals and encode them into global latent vectors. In order to make up for the lack of local dependencies in self-attention network

the local encoder first constructs the session sequences into a session graphs

then the graph neural networks are used to capture the local dependencies among adjacent items and encode them into local latent vectors. Finally

the linear combination of global and local latent vectors obtained from the dual encoder is used to obtain the session representations and the click probability of each candidate item is obtained by decoding the session representions through the prediction layer. Experimental results and comparisons with a single global encoder and a single local encoder show that the combination of the global encoder based on self-attention networks and the local encoder based on graph neural networks improves the hit rate by 3.11% and 6.55%

respectively. Comparisons with state-of-the-art methods on two public datasets validate the effectiveness and feasibility of the proposed method.

关键词

Keywords

references

RENDLE S, FREUDENTHALER C, SCHMIDT T L. Factorizing personalized Markov chains for next-basket recommendation [C]∥Proceedings of the 19th International World Wide Web Conference. New York, USA: ACM, 2010: 811-820.

HIDASI B, KARATZOGLOU A, BALTRUNAS L, et al. Session-based recommendations with recurrent neural networks [EB/OL]. [2020-03-28]. https: ∥arxiv.org/abs/1511.06939.

LI Jing, REN Pengjie, CHEN Zhumin, et al. Neural attentive session-based recommendation [C]∥Proceeding of the 26th ACM Conference on Information and Knowledge Management. New York, USA: ACM, 2017: 1419-1428.

LIU Qiao, ZENG Yifu, MOKHOSI R, et al. Stamp: short-term attention/memory priority model for session-based recommendation [C]∥Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery Data Mining. New York, USA: ACM, 2018: 1831-1839.

REN Pengjie, CHEN Zhumin, LI Jing, et al. RepeatNet: a repeat aware neural recommendation machine for session-based recommendation [C]∥Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Menlo Park, CA, USA: AAAI, 2019: 4806-4813.

WANG Meirui, REN Pengjie, MEI Lei, et al. A collaborative session-based recommendation approach with parallel memory modules [C]∥Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2019: 345-354.

王雅青, 郭彩丽, 楚云霏, 等. 面向会话型推荐系统的个性化分层循环模型 [J]. 北京邮电大学学报, 2019, 42(6): 142-148.

WANG Yaqing, GUO Caili, CHU Yunfei, et al. Personalized hierarchical recurrent model for session-based recommendation systems [J]. Journal of Beijing University of Posts and Telecommunications, 2019, 42(6): 142-148.

曾义夫, 牟其林, 周乐, 等. 基于图表示学习的会话感知推荐模型 [J]. 计算机研究与发展, 2020, 57(3): 590-603.

ZENG Yifu, MU Qilin, ZHOU Le, et al. Graph embedding based session perception model for next-click recommendation [J]. Journal of Computer Research and Development, 2020, 57(3): 590-603.

WU Shu, TANG Yuyuan, ZHU Yanqiao, et al. Session-based recommendation with graph neural networks [C]∥Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Menlo Park, CA, USA: AAAI, 2019: 346-353.

YU Feng, ZHU Yanqiao, LIU Qiang, et al. TAGNN: target attentive graph neural networks for session-based recommendation [C]∥Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2020: 1921-1924.

CHEN Tianwen, WONG R C. Handling information loss of graph neural networks for session-based recommendation [C]∥Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery Data Mining. New York, USA: ACM, 2020: 1172-1180.

赵海燕, 赵佳斌, 陈庆奎, 等. 会话推荐系统 [J]. 小型微型计算机系统, 2019, 40(9): 1869-1875.

ZHAO Haiyan, ZHAO Jiabin, CHEN Qingkui, et al. Session-based recommendation system [J]. Journal of Chinese Computer Systems, 2019, 40(9): 1869-1875.

黄立威, 江碧涛, 吕守业, 等. 基于深度学习的推荐系统研究综述 [J]. 计算机学报, 2018, 41(7): 1619-1647.

HUANG Liwei, JIANG Bitao LÜ Shouye, et al. Survey on deep learning based recommender systems [J]. Chinese Journal of Computers, 2018, 41(7): 1619-1647.

FANG Hui, GUO Guibing, ZHANG Danning, et al. Deep learning-based sequential recommender systems: concepts, algorithms, and evaluations [C]∥19th International Conference on Web Engineering. Berlin, Gernany: Springer Verlag, 2019: 574-577.

VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]∥Red Hook, NY, USA: Neural Information Processing Systems Foundation, 2017: 5999-6009.

ONDREJ B. The WMT 2014 translation task dataset [DB/OL]. [2020-06-10]. http: ∥www.statmt.org/wmt14/translation-task.html.

XU Chengfeng, ZHAO Pengpeng, LIU Yanchi, et al. Graph contextualized self-attention network for session-based recommendation [C]∥28th International Joint Conference on Artificial Intelligence. Palo Alto, CA, USA: AAAI Press, 2019: 3940-3946.

LI Yujia, TARLOW D, BROCKSCHMIDT M, et al. Gated graph sequence neural networks [EB/OL]. [2020-04-11]. https: ∥arxiv.org/abs/1511.05493.

BEN-SHIMON D. The yoochoose dataset [DB/OL]. [2020-06-01]. https: ∥2015.recsyschallenge.com/challenge.html.

SPIRIN N. The diginetica dataset [DB/OL]. [2020-06-01]. https: ∥competitions.codalab.org/competitions/11161.

TAN Y K, XU Xinxing, LIU Yong. Improved recurrent neural networks for session-based recommendations [C]∥Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. New York, USA: ACM, 2016: 17-22.

SARWAR B, KARYPIS G, KONSTAN J, et al. Item-based collaborative filtering recommendation algorithms [C]∥Proceedings of the 10th International World Wide Web Conference. New York, USA: ACM, 2001: 285-295.

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. Arlington, VA, USA: AUAI Press, 2009: 452-461.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

超临界水异常区域热力学特性研究

离子液体改性燃料的电流体动力学效应研究

语义区分和子图整合驱动的知识图谱表示学习方法

超临界二氧化碳向心透平轮背间隙内风阻损失及流动特性研究

融合物理信息与深度算子网络的变压器绕组热-流场快速计算方法