基于全局增强图神经网络的序列推荐

doi:10.11896/jsjkx.210700085

摘要/Abstract

摘要： 已有基于会话的推荐系统大多根据最后一个点击的项目与当前会话的用户偏好的相关性进行推荐,忽略了在其他会话中可能包含了与当前会话相关的项目转换,这些项目转换可能对用户的当前偏好也有一定的影响,因此需要从局部会话和整体会话的角度来综合分析用户偏好;并且这些推荐系统大多忽略了位置信息的重要性,而与预测位置越近的项目可能与当前用户兴趣的相关性越高。针对这些问题,提出一种基于全局增强的图神经网络的推荐模型(GEL-GNN)。GEL-GNN旨在根据所有会话预测用户的行为,它使用GNN来捕获当前会话的全局和局部之间的关系,使用LSTM来捕获全局层面会话间的关系。首先,通过注意力机制层将用户的偏好表示为基于全局层面和局部层面会话兴趣的组合;然后,使用反向位置信息衡量当前位置和预测位置之间的距离,以便更加准确地预测用户行为。在3个真实的数据集上进行了大量的实验,实验结果表明GEL-GNN优于现有的基于会话的图神经网络推荐模型。

关键词: 基于会话的推荐, 图神经网络, 注意力机制, 位置信息

Abstract: Most of the existing session based recommendation systems recommend based on the correlation between the last clicked item and the user preference of the current session,and ignore that there may be item transitions related to the current session in other sessions,while these item transitions may also have a certain impact on users' current preferences Hence,it is indispensable to analyze users' preferences comprehensively from the perspective of local session and global session.Furthermore,most of these recommendation systems ignore the importance of location information,whereas items closer to the predicted location may be more relevant to the current user's interests.To solve these problems,this paper proposes a recommendation model based on global enhanced graph neural network with LSTM(GEL-GNN).GEL-GNN aims to predict the behavior of users according to all sessions,and GNN is employed to capture the global and local relationship of the current session,while LSTM is employed to capture the relationship between sessions at the global level.Firstly,users' preferences are to be translated as a combination of conversation interests based on global and local levels through the attention mechanism layer.Then,the distance between the current position and the predicted position is measured with the reverse position information,so that user behavior can be predicted more accurately.A number of experiments are conducted on three real data sets.Experimental results show that GEL-GNN is superior to the existing session-based graph neural network recommendation models.

Key words: Session-based recommendations, Graph neural network, Attention mechanism, Position information

中图分类号:

TP391

周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐[J]. 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085

ZHOU Fang-quan, CHENG Wei-qing. Sequence Recommendation Based on Global Enhanced Graph Neural Network[J]. Computer Science, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085

参考文献

[1]SCHEDL M,ZAMANI H,CHEN C W,et al.Current challenges and visions in music recommender systems research[J].International Journal of Multimedia Information Retrieval,2018,7(2):95-116.
[2]GE Y,ZHAO S,ZHOU H,et al.Understanding Echo Chambers in E-commerce Recommender Systems[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.China:ACM,2020:2261-2270.
[3]BERNARDI L,KAMPS J,KISELEVA J,et al.The Continuous Cold Start Problem in e-Commerce Recommender Systems[J].Computer Science,2015,92(2):28002-28007.
[4]KUMAR P,THAKUR R S.Recommendation system tech-niques and related issues:a survey[J].International Journal of Information Technology,2018,10(4):495-501.
[5]LI Z,ZHAO H,LIU Q,et al.Learning from history and pre-sent:Next-item recommendation via discriminatively exploiting user behaviors[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mi-ning.London:ACM,2018:1734-1743.
[6]SARWAR B,KARYPIS G,KONSTAN J,et al.Item-based collaborative filtering recommendation algorithms[C]//Procee-dings of the 10th International Conference on World Wide Web.Hong Kong:ACM,2001:285-295.
[7]SHANI G,HECKERMAN D,BRAFMAN R I,et al.An MDP-based recommender system[J].Journal of Machine Learning Research,2005,6(9):1265-1295.
[8]HIDASI B,KARATZOGLOU A,BALTRUNAS L,et al.Session-based Recommendations with Recurrent Neural Networks[J].arXiv:1511.06939,2015.
[9]TAN Y K,XU X,LIU Y.Improved recurrent neural networks for session-based recommendations[C]//Proceedings of the 1st workshop on deep learning for recommender systems.Boston:ACM,2016:17-22.
[10]TUAN T X,PHUONG T M.3D convolutional networks for session-based recommendation with content features[C]//Proceedings of the eleventh ACM conference on recommender systems.New York,NY,USA:ACM.2017:138-146.
[11]LI J,REN P,CHEN Z,et al.Neural attentive session-based recommendation[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management.Singapore:ACM,2017:1419-1428.
[12]TSAI C H,BRUSILOVSKY P,RAHDARI B.Exploring User-Controlled Hybrid Recommendation in a Conference Context[C]//Joint Proceeding of the ACM IUI 2019 Workshops.Los Angeles:[s.n.],2019:1-6.
[13]QIAN Y,ZHANG Y,MA X,et al.EARS:Emotion-aware re-commender system based on hybrid information fusion[J].Information Fusion,2019,46:141-146.
[14]MNIH A,SALAKHUTDINOV R R.Probabilistic matrix fac-torization[J].Advances in Neural Information Processing Systems,2007,20:1257-1264.
[15]KOREN Y,BELL R.Advances in collaborative filtering[Z].Recommender Systems Handbook,2015:77-118.
[16]SHANI G,HECKERMAN D,BRAFMAN R I,et al.An MDP-based recommender system[J].Journal of Machine Learning Research,2005,6(1):1265-1295.
[17]RENDLE S,FREUDENTHALER C,SCHMIDT-THIEME L.Factorizing personalized markov chains for next-basket recommendation[C]//Proceedings of the 19th International Confe-rence on World Wide Web.2010:811-820.
[18]SUTSKEVER I,VINYALS O,LEQ V.Sequence to sequencelearning with neural networks[C]//Advances in Neural Information Processing Systems.2014:3104-3112.
[19]LIU Q,ZENG Y,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.London:ACM,2018:1831-1839.
[20]WU S,TANG Y,ZHU Y,et al.Session-based recommendation with graph neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence.USA:AAAI,2019:346-353.
[21]MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality[C]//Advances in Neural Information Processing Systems.USA:MIT Press,2013:3111-3119.
[22]PEROZZI B,AL-RFOU R,SKIENA S.Deepwalk:Online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2014:701-710.
[23]TANG J,QU M,WANG M,et al.Line:Large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web.Italy:ACM,2015:1067-1077.
[24]GROVER A,LESKOVEC J.node2vec:Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mi-ning.United States:ACM,2016:855-864.
[25]DUVENAUD D,MACLAURIN D,AGUILERA-IPARRAGUIRRE J,et al.Convolutional networks on graphs for learning molecular fingerprints[J].arXiv:1509.09292,2015.
[26]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[27]WANG H,XIAO G,HAN N,et al.Session-Based Graph Convolutional ARMA Filter Recommendation Model[J].IEEE Access,2020,8:62053-62064.
[28]LIU E,CHU Y,LUAN L,et al.Mixing-RNN:a recommendation algorithm based on recurrent neural network[C]//International Conference on Knowledge Science,Engineering and Ma-nagement.Athens:Springer,2019:109-117.
[29]HUANG R,WANG N,HAN C,et al.TNAM:A tag-aware neural attention model for Top-N recommendation[J].Neurocomputing,2020,385:1-12.
[30]SONG W,XIAO Z,WANG Y,et al.Session-based social recommendation via dynamic graph attention networks[C]//Procee-dings of the Twelfth ACM International Conference on Web Search and Data Mining.Australia:ACM,2019:555-563.
[31]WU Q,ZHANG H,GAO X,et al.Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems[C]//The World Wide Web Conference.USA:ACM,2019:2091-2102.
[32]MU N,ZHA D,HE Y,et al.Graph Attention Networks for Neural Social Recommendation[C]//2019 IEEE 31st International Conference on Tools with Artificial Intelligence(ICTAI).Portland:IEEE,2019:1320-1327.
[33]TAO Z,WEI Y,WANG X,et al.MGAT:Multimodal Graph Attention Network for Recommendation[J].Information Proces-sing & Management,2020,57(5):102277.
[34]YUAN Z,LIU H,LIU Y,et al.Spatio-Temporal Dual Graph Attention Network for Query-POI Matching[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.China:ACM,2020:629-638.
[35]GREFF K,SRIVASTAVA R K,KOUTNÍK J,et al.LSTM:A search space odyssey[J].IEEE Transactions on Neural Networks and Learning Systems,2016,28(10):2222-2232.

相关文章 15

[1]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[2]	戴禹, 许林峰. 基于文本行匹配的跨图文本阅读方法 Cross-image Text Reading Method Based on Text Line Matching 计算机科学, 2022, 49(9): 139-145. https://doi.org/10.11896/jsjkx.220600032
[3]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[4]	熊丽琴, 曹雷, 赖俊, 陈希亮. 基于值分解的多智能体深度强化学习综述 Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization 计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112
[5]	姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[6]	汪鸣, 彭舰, 黄飞虎. 基于多时间尺度时空图网络的交通流量预测模型 Multi-time Scale Spatial-Temporal Graph Neural Network for Traffic Flow Prediction 计算机科学, 2022, 49(8): 40-48. https://doi.org/10.11896/jsjkx.220100188
[7]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[8]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[9]	闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[10]	齐秀秀, 王佳昊, 李文雄, 周帆. 基于概率元学习的矩阵补全预测融合算法 Fusion Algorithm for Matrix Completion Prediction Based on Probabilistic Meta-learning 计算机科学, 2022, 49(7): 18-24. https://doi.org/10.11896/jsjkx.210600126
[11]	杨炳新, 郭艳蓉, 郝世杰, 洪日昌. 基于数据增广和模型集成策略的图神经网络在抑郁症识别上的应用 Application of Graph Neural Network Based on Data Augmentation and Model Ensemble in Depression Recognition 计算机科学, 2022, 49(7): 57-63. https://doi.org/10.11896/jsjkx.210800070
[12]	张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[13]	曾志贤, 曹建军, 翁年凤, 蒋国权, 徐滨. 基于注意力机制的细粒度语义关联视频-文本跨模态实体分辨 Fine-grained Semantic Association Video-Text Cross-modal Entity Resolution Based on Attention Mechanism 计算机科学, 2022, 49(7): 106-112. https://doi.org/10.11896/jsjkx.210500224
[14]	徐鸣珂, 张帆. Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法 Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition 计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085
[15]	孟月波, 穆思蓉, 刘光辉, 徐胜军, 韩九强. 基于向量注意力机制GoogLeNet-GMP的行人重识别方法 Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism 计算机科学, 2022, 49(7): 142-147. https://doi.org/10.11896/jsjkx.210600198

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed