Please wait a minute...
Advanced Search
数据分析与知识发现  2021, Vol. 5 Issue (11): 124-134     https://doi.org/10.11925/infotech.2096-3467.2021.0136
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
嵌入隐式相似群的深度协同过滤算法*
李振宇,李树青()
南京财经大学信息工程学院 南京 210023
Deep Collaborative Filtering Algorithm with Embedding Implicit Similarity Groups
Li Zhenyu,Li Shuqing()
College of Information Engineering, Nanjing University of Finance & Economics, Nanjing 210023, China
全文: PDF (1182 KB)   HTML ( 5
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】 构建能捕获局部关联和表达用户显隐式偏好的深度协同过滤模型。【方法】 在显式推荐任务中嵌入利用隐式反馈查找的相似群,通过多层感知机分别同时对用户-项目、用户-相似项目群、项目-相似用户群进行建模。【结果】 在MovieLens两个数据集上的实验表明,该模型较各类协同过滤推荐算法的MAE和RMSE降低幅度分别最高达10.94%和11.79%。【局限】 使模型达到最佳性能的近邻数在不同数据集存在差异,最佳近邻数的确认问题有待探索。【结论】 该模型通过嵌入隐式相似群能有效弥补局限,使推荐结果更准确。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
李振宇
李树青
关键词 局部关联显隐式偏好深度协同过滤    
Abstract

[Objective] This paper tries to construct a deep collaborative filtering model that can capture local relevance as well as explicit / implicit feedbacks. [Methods] In the explicit recommendation tasks, we embedded similar groups found by implicit feedback search. Then, we create models for user-item group, user-similar-item group, and item-similar-user group with Multi-Layer Perceptron. [Results] We examined the new algorithm with MovieLens datasets. Compared with existing methods, the MAE and RMSE of our model were reduced by 10.94% and 11.79% respectively. [Limitations] More research is needed to identify the optimal number of the nearest neighbors for different datasets. [Conclusions] The new model could more effectively generate the recommendation results.

Key wordsLocal Relevance    Explicit and Implicit Preference    Deep Collaborative Filtering
收稿日期: 2021-02-08      出版日期: 2021-12-23
ZTFLH:  TP391  
基金资助:*江苏省高等学校自然科学研究重大项目(19KJA510011)
通讯作者: 李树青,ORCID:0000-0001-9814-5766     E-mail: leeshuqing@163.com
引用本文:   
李振宇, 李树青. 嵌入隐式相似群的深度协同过滤算法*[J]. 数据分析与知识发现, 2021, 5(11): 124-134.
Li Zhenyu, Li Shuqing. Deep Collaborative Filtering Algorithm with Embedding Implicit Similarity Groups. Data Analysis and Knowledge Discovery, 2021, 5(11): 124-134.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2021.0136      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2021/V5/I11/124
Fig.1  NCF框架基本原理
Fig.2  IsMLP通用框架
Fig.3  IsMLP向量学习原理
Fig.4  IsMLP评分预测模型
数据集 用户数量 项目数量 评分数量 稀疏度
MovieLens-100k 943 1 682 100 000 93.7%
MovieLens-Latest-small 610 9 724 100 836 98.3%
Table 1  数据集信息
损失
函数
优化器 向量嵌入维度 正则化 激活
函数
潜在
因子数
批量
大小
MSE RMSprop 64 L2 ReLU 32 64
Table 2  神经网络参数设置
Fig.5  MovieLens-100k实验结果
Fig.6  MovieLens-Latest-Small实验结果
模型 RMSE MAE
IsMLP-M 0.915 4 0.717 5
IsMLP-C 0.925 3 0.718 5
KNN-basic 1.021 5 0.806 9
KNN-withMeans 0.957 5 0.753 9
MF 0.948 9 0.740 9
MLP 0.952 7 0.741 3
NeuMF 0.938 1 0.730 3
Table 3  MovieLens-100k最优结果对比
模型 RMSE MAE
IsMLP-M 0.866 8 0.660 4
IsMLP-C 0.867 9 0.660 7
KNN-basic 0.973 2 0.748 7
KNN-withMeans 0.902 7 0.690 7
MF 0.887 3 0.674 4
MLP 0.888 0 0.674 9
NeuMF 0.879 7 0.673 3
Table 4  MovieLens-Latest-Small最优结果对比
Fig.7  IsMLP和EsMLP对比
[1] Ricci F, Rokach L, Shapira B. Recommender Systems: Introduction and Challenges[A]//Recommender Systems Handbook[M]. Boston, MA: Springer, 2015: 1-34.
[2] Lu J, Wu D S, Mao M S, et al. Recommender System Application Developments: A Survey[J]. Decision Support Systems, 2015, 74:12-32.
doi: 10.1016/j.dss.2015.03.008
[3] Goldberg K, Roeder T, Gupta D, et al. Eigentaste: A Constant Time Collaborative Filtering Algorithm[J]. Information Retrieval, 2001, 4(2):133-151.
doi: 10.1023/A:1011419012209
[4] Koren Y, Bell R, Volinsky C. Matrix Factorization Techniques for Recommender Systems[J]. Computer, 2009, 42(8):30-37.
[5] Xue H J, Dai X Y, Zhang J B, et al. Deep Matrix Factorization Models for Recommender Systems[C]// Proceedings of the 26th International Joint Conference on Artificial Intelligence. 2017: 3203-3209.
[6] Salakhutdinov R, Mnih A, Hinton G. Restricted Boltzmann Machines for Collaborative Filtering[C]// Proceedings of the 24th International Conference on Machine Learning. 2007: 791-798.
[7] Sedhain S, Menon A K, Sanner S, et al. AutoRec: Autoencoders Meet Collaborative Filtering[C]// Proceedings of the 24th International Conference on World Wide Web. 2015: 111-112.
[8] Liang H Z, Baldwin T. A Probabilistic Rating Auto-Encoder for Personalized Recommender Systems[C]// Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. 2015: 1863-1866.
[9] Li S, Kawale J, Fu Y. Deep Collaborative Filtering via Marginalized Denoising Auto-encoder[C]// Proceedings of the 24th ACM International Conference on Information and Knowledge Management. 2015: 811-820.
[10] Ouyang Y X, Liu W Q, Rong W G, et al. Autoencoder-Based Collaborative Filtering[C]// Proceedings of International Conference on Neural Information Processing. Springer, Cham, 2014: 284-291.
[11] Kim D, Park C, Oh J, et al. Convolutional Matrix Factorization for Document Context-Aware Recommendation[C]// Proceedings of the 10th ACM Conference on Recommender Systems. 2016: 233-240.
[12] Singhal A, Sinha P, Pant R. Use of Deep Learning in Modern Recommendation System: A Summary of Recent Works[OL]. arXiv Preprint, arXiv: 1712.07525.
[13] He X N, Liao L Z, Zhang H W, et al. Neural collaborative filtering[C]// Proceedings of the 26th International Conference on World Wide Web. 2017: 173-182.
[14] Zheng Y, Liu C L, Tang B S, et al. Neural Autoregressive Collaborative Filtering for Implicit Feedback[C]// Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. 2016: 2-6.
[15] Chen W Y, Cai F, Chen H H, et al. Joint Neural Collaborative Filtering for Recommender Systems[J]. ACM Transactions on Information Systems, 2019, 37(4):1-30.
[16] He X N, Du X, Y Wang X, et al. Outer Product-Based Neural Collaborative Filtering[OL]. arXiv Preprint, arXiv: 1808.03912.
[17] Bai T, Wen J R, Zhang J, et al. A Neural Collaborative Filtering Model with Interaction-Based Neighborhood[C]// Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. 2017: 1979-1982.
[18] Ebesu T, Shen B, Fang Y. Collaborative Memory Network for Recommendation Systems[C]// Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. 2018: 515-524.
[19] Deng Z H, Huang L, Wang C D, et al. DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System[C]// Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1):61-68.
[20] Koren Y. Factorization Meets the Neighborhood: A Multifaceted Collaborative Filtering Model[C]// Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2008: 426-434.
[21] Liu N N, Xiang E W, Zhao M, et al. Unifying Explicit and Implicit Feedback for Collaborative Filtering[C]// Proceedings of the 19th ACM International Conference on Information and Knowledge Management. 2010: 1445-1448.
[22] Xie R B, Ling C, Wang Y L, et al. Deep Feedback Network for Recommendation[C] // Proceedings of the 29th International Joint Conference on Artificial Intelligence. 2020.
[23] Zamani H, Croft W B. Learning a Joint Search and Recommendation Model from User-Item Interactions[C]// Proceedings of the 13th International Conference on Web Search and Data Mining. 2020: 717-725.
[1] 王鸿, 舒展, 高印权, 田文洪. 一种单分类器联合多任务网络的隐式句间关系分析方法*[J]. 数据分析与知识发现, 2021, 5(11): 80-88.
[2] 吴彦文, 蔡秋亭, 刘智, 邓云泽. 融合多源数据和场景相似度计算的数字资源推荐研究*[J]. 数据分析与知识发现, 2021, 5(11): 114-123.
[3] 董淼, 苏中琪, 周晓北, 兰雪, 崔志刚, 崔雷. 利用Text-CNN改进PubMedBERT在化学诱导性疾病实体关系分类效果的尝试[J]. 数据分析与知识发现, 2021, 5(11): 145-152.
[4] 余传明, 张贞港, 孔令格. 面向链接预测的知识图谱表示模型对比研究*[J]. 数据分析与知识发现, 2021, 5(11): 29-44.
[5] 丁浩, 艾文华, 胡广伟, 李树青, 索炜. 融合用户兴趣波动时序的个性化推荐模型*[J]. 数据分析与知识发现, 2021, 5(11): 45-58.
[6] 华斌, 吴诺, 贺欣. 基于知识融合的政务信息化项目多专家审批意见整合*[J]. 数据分析与知识发现, 2021, 5(10): 124-136.
[7] 王媛, 时恺泽, 牛振东. 一种用于实体关系三元组抽取的位置辅助分步标记方法*[J]. 数据分析与知识发现, 2021, 5(10): 71-80.
[8] 杨辰, 陈晓虹, 王楚涵, 刘婷婷. 基于用户细粒度属性偏好聚类的推荐策略*[J]. 数据分析与知识发现, 2021, 5(10): 94-102.
[9] 戴志宏, 郝晓玲. 上下位关系抽取方法及其在金融市场的应用*[J]. 数据分析与知识发现, 2021, 5(10): 60-70.
[10] 汪雪锋, 任惠超, 刘玉琴. 融合聚类信息的技术主题图可视化方法研究 [J]. 数据分析与知识发现, 0, (): 1-.
[11] 王一钒,李博,史话,苗威,姜斌. 古汉语实体关系联合抽取的标注方法*[J]. 数据分析与知识发现, 2021, 5(9): 63-74.
[12] 车宏鑫,王桐,王伟. 前列腺癌预测模型对比研究*[J]. 数据分析与知识发现, 2021, 5(9): 107-114.
[13] 周阳,李学俊,王冬磊,陈方,彭莉娟. 炸药配方设计知识图谱的构建与可视分析方法研究*[J]. 数据分析与知识发现, 2021, 5(9): 42-53.
[14] 马江微, 吕学强, 游新冬, 肖刚, 韩君妹. 融合BERT与关系位置特征的军事领域关系抽取方法*[J]. 数据分析与知识发现, 2021, 5(8): 1-12.
[15] 刘渊晨, 王昊, 高亚琪. 在线音乐歌单播放量预测及影响因素分析*[J]. 数据分析与知识发现, 2021, 5(8): 100-112.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn