计算机科学 ›› 2019, Vol. 46 ›› Issue (6): 41-48.doi: 10.11896/j.issn.1002-137X.2019.06.005

• 大数据与数据科学* • 上一篇    下一篇

融合node2vec和深度神经网络的隐式反馈推荐模型

何瑾琳, 刘学军, 徐新艳, 毛宇佳   

  1. (南京工业大学计算机科学与技术学院 南京211816)
  • 收稿日期:2018-06-15 发布日期:2019-06-24
  • 通讯作者: 刘学军(1970-),男,博士,教授,CCF高级会员,主要研究方向为数据库、数据挖掘、推荐系统等,E-mail:lxj_njgd@163.com
  • 作者简介:何瑾琳(1995-),女,硕士生,主要研究方向为数据挖掘、推荐系统,E-mail:hejinlin00@outlook.com;徐新艳(1980-),女,讲师,主要研究方向为数据挖掘、智能信息处理;毛宇佳(1994-),男,硕士生,主要研究方向为数据挖掘、推荐系统。
  • 基金资助:
    江苏省重点研发计划项目(BE2017617,BE2015697),国家重点研发计划子课题(2017YFC0805605)资助。

Implicit Feedback Recommendation Model Combining Node2vec and Deep Neural Networks

HE Jin-lin, LIU Xue-jun, XU Xin-yan, MAO Yu-jia   

  1. (School of Computer Science and Technology,Nanjing Tech University,Nanjing 211816,China)
  • Received:2018-06-15 Published:2019-06-24

摘要: 利用隐式反馈信息实现个性化推荐是实用且具有挑战性的研究课题。对如何有效结合辅助信息来解决数据稀疏问题从而实现高效推荐的问题进行了研究,提出了一种融合node2vec和深度神经网络的隐式反馈推荐模型。该模型采用一种嵌入元数据的深度神经网络框架(Deep Neural Network Framework with Embedded Meta-data,Meta-DNN),首先将用户和项目的one-hot向量进行低维映射,再嵌入元数据信息,并结合node2vec的二阶随机游走方法学习网络中的邻居节点,使得相邻节点具有相似的节点表示,同时通过增强相邻用户和项目的平滑度来缓解数据稀疏性;最后使用深度神经网络进一步学习用户对项目的偏好,进而为用户产生推荐。其中,还引入了流行度参数对未知项目进行非平均抽样,优化隐式反馈负采样策略。在Gowalla和MovieLens-1M两个数据集上的实验表明,所提方法可以明显提高系统的预测性能和推荐质量。

关键词: node2vec, 推荐系统, 神经网络, 深度学习, 隐式反馈, 元数据

Abstract: It is extremely practical and challenging to implement personalized recommendation based on large-scale implicit feedback information.In order to solve the problem of data sparseness and then achieve effective recommendation combining various side information,this paper proposed an implicit feedback recommendation model combining node2vec and deep neural networks.This model utilizes a deep neural network framework with embedded meta-data(Meta-DNN),and maps the users and items vectors in a low-dimensional manner.Wherein,the second-order random walk of node2vec is used to learn neighbor nodes in the network with embedded meta-data so that adjacent nodes have similar node representations.Besides,data sparsity is alleviated via improving the smoothness among neighboring users and items.Finally,deep neural network is used for further learning user preferences for items,thus providing recommendation for users.In addition,the popularity parameter is introduced to perform non-average sampling of unknown items and an implicit feedback negative sampling strategy is optimized.Experimental results on the typical Gowalla and Mo-vieLens-1M data sets demonstrate the prediction performance and recommendation quality of the proposed model compared with state-of-the-art recommendation algorithms.

Key words: Node2vec, Recommender system, Neural networks, Deep learning, Implicit feedback, Meta-data

中图分类号: 

  • TP391
[1]LI X,CONG G,LI X L,et al.Rank-GeoFM:A Ranking based Geographical Factorization Method for Point of Interest Recommendation[C]∥International ACM SIGIR Conference on Research and Development in Information Retrieval.Santiago:ACM,2015:433-442.
[2]HE X,ZHANG H,KAN M Y,et al.Fast Matrix Factorization for Online Recommendation with Implicit Feedback[C]∥International ACM SIGER Conference on Research & Development in Information Retrieval.Pisa:ACM,2016:549-558.
[3]WANG H,WANG N,YEUNG D Y.Collaborative Deep Lear-ning for Recommender Systems[C]∥ACM SIGKDD Internatio-nal Conference on Knowledge Discovery and Data Mining.Sydney:ACM,2015:1235-1244.
[4]SHENG L,JAYA K,YUN F.Deep Collaborative Filtering via Marginalized Denoising Auto-encoder[C]∥ACM International on Conference on Information and Knowledge Management.Melbourne:ACM,2015:811-820.
[5]HE X,LIAO L,ZHANG H,et al.Neural Collaborative Filtering [C]∥International Conference on World Wide Web.Perth:ACM,2017:173-182.
[6]MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed Representations of Words and Phrases and their Compositionality [J].Advances in Neural Information Processing Systems,2013,26:3111-3119.
[7]VASILE F,SMIRNOVA E,CONNEAU A.Meta-Prod2Vec: Product Embeddings Using Side-Information for Recommendation[C]∥ACM Conference on Recommender Systems.Boston:ACM,2016:225-232.
[8]HANDCOCK M S,RAFTERY A E,TANTRUM J M.Model-based clustering for social networks [J].Journal of the Royal Statistical Society,2007,170(2):301-354.
[9]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.International World Wide Web Conferences Steering Committee,2015:1067-1077.
[10]PERPZZIE B,Al-RFOU R,SKIENA S.Deepwalk:online lear-ning of social representations[C]∥Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining.New York:ACM,2014:701-710.
[11]GROVER A,LESKOVEC J.node2vec:Scalable Feature Lear-ning for Networks [C]∥Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Francisco:ACM,2016:855-864.
[12]YANG Z,COHEN W W,SALAKHUTDINOV R.Revisiting semi-supervised learning with graph embeddings[C]∥International Conference on International Conference on Machine Learning.New York:ICML,2016:40-48.
[13]LU Y,CAO J.Research Status and Future Trends of Recom-mender Systems for Implicit Feedback [J].Computer Science,2016,43(4):7-15.(in Chinese)
陆艺,曹健.面向隐式反馈的推荐系统研究现状与趋势[J].计算机科学,2016,43(4):7-15.
[14]YAO W,HE J,HUANG G,et al.A graph-based model for context-aware recommendation using implicit feedback data [J].World Wide Web-internet & Web Information Systems,2015,18(5):1351-1371.
[15]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Ima-ge Recognition[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:770-778.
[16]ZHANG C,SHOU L,CHEN K,et al.Evaluating geo-social influence in location-based social networks[C]∥ACM International Conference on Information and Knowledge Management.Maui:ACM,2012:1442-1451.
[17]YIN J,WANG Z S,LI Q,et al.Personalized recommendation based on large-scale implicit feedback[J].Journal of Software,2014,5(9):1953-1966.(in Chinese)
印鉴,王智圣,李琪,等.基于大规模隐式反馈的个性化推荐[J].软件学报,2014,5(9):1953-1966 [18]RENDLE S,FREUDENTHALER C,GANTNER Z,et al.BPR:Bayesian personalized ranking from implicit feedback [C]∥Conference on Uncertainty in Artificial Intelligence.Montreal:AUAI Press,2009:452-461.
[19]HU Y,KOREN Y,VOLINSKY C.Collaborative Filtering for Implicit Feedback Datasets[C]∥IEEE International Conference on Data Mining.Leipzig:IEEE,2009:263-272.
[1] 周燕, 曾凡智, 吴臣, 罗粤, 刘紫琴. 基于深度学习的三维形状特征提取方法[J]. 计算机科学, 2019, 46(9): 47-58.
[2] 马露, 裴伟, 朱永英, 王春立, 王鹏乾. 基于深度学习的跌倒行为识别[J]. 计算机科学, 2019, 46(9): 106-112.
[3] 李青华, 李翠平, 张静, 陈红, 王绍卿. 深度神经网络压缩综述[J]. 计算机科学, 2019, 46(9): 1-14.
[4] 王鑫, 孟浩浩, 姜小涛, 陈胜勇, 孙凌云. 基于神经网络的角色运动合成研究进展[J]. 计算机科学, 2019, 46(9): 22-27.
[5] 王嫣然, 陈清亮, 吴俊君. 面向复杂环境的图像语义分割方法综述[J]. 计算机科学, 2019, 46(9): 36-46.
[6] 孙中锋, 王静. 用于基于方面情感分析的RCNN-BGRU-HN网络模型[J]. 计算机科学, 2019, 46(9): 223-228.
[7] 缪永伟, 李高怡, 鲍陈, 张旭东, 彭思龙. 基于卷积神经网络的图像局部风格迁移[J]. 计算机科学, 2019, 46(9): 259-264.
[8] 江泽涛, 秦嘉奇, 胡硕. 基于多路卷积神经网络的多光谱场景识别方法[J]. 计算机科学, 2019, 46(9): 265-270.
[9] 石晓红, 黄钦开, 苗佳欣, 苏卓. 基于卷积网络的边缘保持滤波方法[J]. 计算机科学, 2019, 46(9): 277-283.
[10] 邓存彬, 虞慧群, 范贵生. 融合动态协同过滤和深度学习的推荐算法[J]. 计算机科学, 2019, 46(8): 28-34.
[11] 杜威, 丁世飞. 多智能体强化学习综述[J]. 计算机科学, 2019, 46(8): 1-8.
[12] 张艳红, 张春光, 周湘贞, 王怡鸥. 项目多属性模糊联合的多样性视频推荐算法[J]. 计算机科学, 2019, 46(8): 78-83.
[13] 郭旭, 朱敬华. 基于用户向量化表示和注意力机制的深度神经网络推荐模型[J]. 计算机科学, 2019, 46(8): 111-115.
[14] 张义杰, 李培峰, 朱巧明. 基于自注意力机制的事件时序关系分类方法[J]. 计算机科学, 2019, 46(8): 244-248.
[15] 于洋, 李世杰, 陈亮, 刘韵婷. 基于改进YOLO v2的船舶目标检测方法[J]. 计算机科学, 2019, 46(8): 332-336.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75, 88 .
[2] 夏庆勋,庄毅. 一种基于局部性原理的远程验证机制[J]. 计算机科学, 2018, 45(4): 148 -151, 162 .
[3] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[4] 王振武,吕小华,韩晓辉. 基于四叉树分割的地形LOD技术综述[J]. 计算机科学, 2018, 45(4): 34 -45 .
[5] 王振朝,侯欢欢,连蕊. 抑制CMT中乱序程度的路径优化方案[J]. 计算机科学, 2018, 45(4): 122 -125 .
[6] 廖星,袁景凌,陈旻骋. 一种自适应权重的并行PSO快速装箱算法[J]. 计算机科学, 2018, 45(3): 231 -234, 273 .
[7] 张景,朱国宾. 基于CBOW-LDA主题模型的Stack Overflow编程网站热点主题发现研究[J]. 计算机科学, 2018, 45(4): 208 -214 .
[8] 朱文强. 面向O2O服务的移动社交网络个性化可信群体识别模型[J]. 计算机科学, 2018, 45(6): 76 -83 .
[9] 丁舒阳,黎冰,侍洪波. 基于改进的离散PSO算法的FJSP的研究[J]. 计算机科学, 2018, 45(4): 233 -239, 256 .
[10] 侯彦娥,孔云峰,党兰学. 求解多车型校车路径问题的混合集合划分的GRASP算法[J]. 计算机科学, 2018, 45(4): 240 -246 .