LIU Yu-ning,TAO Hong-cai.Design and Implementation of the RecommendationSystem for Douban Group based on RBM Model[J].Journal of Chengdu University of Information Technology,2018,(02):107-112.[doi:10.16836/j.cnki.jcuit.2018.02.001]
基于RBM模型的豆瓣小组推荐系统设计与实现
- Title:
- Design and Implementation of the RecommendationSystem for Douban Group based on RBM Model
- 文章编号:
- 2096-1618(2018)02-0107-06
- Keywords:
- douban group; recommendation system; RBM; contrastive divergence
- 分类号:
- TP301.6
- 文献标志码:
- A
- 摘要:
- 将受限玻尔兹曼机(restricted boltzmann machine, RBM)模型应用于推荐领域已成为一个很有意义的研究方向。针对豆瓣小组,设计实现了一个基于RBM模型的推荐系统,该系统由数据层、模型层、评测层3部分组成。数据层通过选取“豆瓣达人”数据,一定程度上解决了数据稀疏问题。模型层利用对比散度(contrastive divergence, CD)算法进行学习。实验结果表明,在豆瓣小组数据集上,RBM模型相较传统协同过滤算法具有更好的推荐效果。
- Abstract:
- Restricted Boltzmann Machine for recommendation has become one of the significant researches. In this paper,a recommendation system for Douban Group based on RBM model is designed and implemented.The system consists of three layers:data layer,model layer and evaluation layer.The data layer can solve the problem of data sparsity to a certain extent by selecting the data of “the Douban expert”.The experimental results show that the RBM model rivals the traditional collaborative filtering algorithm by providing a better recommendation effect on the data set of the Douban Group.
参考文献/References:
[1] Linden G,Smith B,York J Amazon.Com Recommendations:Item-to-Item Collaborative Filtering[J].IEEE Internet Computing,2003,7(1):76-80.
[2] Georgiev K,Nakov P.A non-IID framework for collaborative filtering with restricted Boltzmann machines[C].International Conference on International Conference on Machine Learning.JMLR.org,2013:1148-1156.
[3] Lecun Y, Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436-444.
[4] Salakhutdinov R, Mnih A,Hinton G.Restricted Boltzmann machines for collaborative filtering[C].International Conference on Machine Learning.ACM,2007:791-798.
[5] Hu L,Cao J,Xu G,et al.Deep modeling of group preferences for group-based recommendation[C].Twenty-Eighth AAAI Conference on Artificial Intelligence.AAAI Press,2014:1861-1867.
[6] Wang X,Wang Y.Improving Content-based and Hybrid Music Recommendation using Deep Learning[C].ACM International Conference on Multimedia. ACM,2014:627-636.
[7] Yon R.Music Personalization at Spotify[C].ACM Conference on Recommender Systems.ACM,2016:373-373.
[8] Liu Q,Wu S,Wang L,et al.Predicting the next location: a recurrent model with spatial and temporal contexts[C].Thirtieth AAAI Conference on Artificial Intelligence.AAAI Press,2016:194-200.
[9] Wang S,Wang Y,Tang J,et al.What Your ImagesReveal:Exploiting Visual Contents for Point-of-Interest Recommendation[C].The International Conference,2017:391-400.
[10] 张春霞,姬楠楠,王冠伟.受限波尔兹曼机简介[J].工程数学学报,2013(2):159-173.
[11] Roux N L,Bengio Y.Representational power of restricted boltzmann machines and deep belief networks[J].Neural Computation,2008,20(6):1631.
[12] Hinton G E.Training products of experts by minimizing contrastive divergence [M].MIT Press,2002.
[13] Covington P,Adams J,Sargin E.Deep Neural Networks for YouTube Recommendations[C]. ACM Conference on Recommender Systems.ACM,2016:191-198.
[14] Amatriain X,Lathia N,Pujol J M,et al.The wisdom of the few:a collaborative filtering approach based on expert opinions from the web[C].International ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,2009:532-539.
[15] 罗恒.基于协同过滤视角的受限玻尔兹曼机研究[D].上海:上海交通大学,2011.
[16] Geoffrey E.Hinton.A Practical Guide to Training Restricted Boltzmann Machines[J].Momentum,2012,9(1):599-619.
[17] 何洁月,马贝.利用社交关系的实值条件受限玻尔兹曼机协同过滤推荐算法[J].计算机学报,2016(1):183-195.
相似文献/References:
[1]孙琛恺,安俊秀.用于评价推荐系统的多样性指数的研究[J].成都信息工程大学学报,2021,36(03):253.[doi:10.16836/j.cnki.jcuit.2021.03.002]
SUN Chenkai,AN Junxiu.Research on Diversity Index for Evaluating Recommendation System[J].Journal of Chengdu University of Information Technology,2021,36(02):253.[doi:10.16836/j.cnki.jcuit.2021.03.002]
备注/Memo
收稿日期:2018-01-13基金项目:国家自然科学基金资助项目(61505168)