基于深度学习加强的混合推荐方法

张敏; 丁弼原; 马为之; 谭云志; 刘奕群; 马少平

doi:10.16511/j.cnki.qhdxxb.2017.25.039

PDF(1022 KB)

清华大学学报（自然科学版） ›› 2017, Vol. 57 ›› Issue (10) : 1014-1021. DOI: 10.16511/j.cnki.qhdxxb.2017.25.039

计算机科学与技术

基于深度学习加强的混合推荐方法

张敏, 丁弼原, 马为之, 谭云志, 刘奕群, 马少平

作者信息 +

Hybrid recommendation approach enhanced by deep learning

ZHANG Min, DING Biyuan, MA Weizhi, TAN Yunzhi, LIU Yiqun, MA Shaoping

Author information +

文章历史 +

摘要

近年来基于矩阵分解的协同过滤算法在评分预测上取得了显著成果，但仍未能很好地解决冷启动、数据稀疏等问题。因此，如何将评论信息引入推荐系统以缓解上述问题成为研究的热点之一。该文尝试基于深度学习来加强个性化推荐，提出将层叠降噪自动编码器（stacked denoising auto-encoder，SDAE）与隐含因子模型（latent factor model，LFM）相结合的混合推荐方法，综合考虑评论文本与评分，以提升推荐模型对潜在评分预测的准确性。在常用大规模公开Amazon数据集上进行的测试结果表明：与传统推荐模型相比，该文提出的方法可有效提高评分预测的准确性，性能提升最高可达64.43%。

Abstract

Collaborative filtering based on matrix factorization has been very successful, while cold-start and data sparseness problems have not been well resolved. Hence, many studies have attempted to include review information into rating predictions. This paper presents a hybrid model that introduces deep learning into recommendation system with collaborative filtering. The algorithm combines a stacked denoising auto encoder (SDAE) with a latent factor model (LFM) to make use of both review and rating information to improve the rating predictions. Evaluations on a large, commonly used Amazon dataset show that this approach significantly improves the rating prediction accuracy in comparison with traditional models, with up to 64.43% better predictions.

导出引用

张敏, 丁弼原, 马为之, 谭云志, 刘奕群, 马少平. 基于深度学习加强的混合推荐方法[J]. 清华大学学报（自然科学版）. 2017, 57(10): 1014-1021 https://doi.org/10.16511/j.cnki.qhdxxb.2017.25.039

ZHANG Min, DING Biyuan, MA Weizhi, TAN Yunzhi, LIU Yiqun, MA Shaoping. Hybrid recommendation approach enhanced by deep learning[J]. Journal of Tsinghua University(Science and Technology). 2017, 57(10): 1014-1021 https://doi.org/10.16511/j.cnki.qhdxxb.2017.25.039

中图分类号： TP391.2

参考文献

[1] Koren Y, Bell R, Volinsky C. Matrix factorization techniques for recommender systems[J]. IEEE Computer, 2009, 42(8):30-37.[2] Koran 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 (KDD'08). Las Vegas, NV, USA:ACM, 2008:426-434.[3] Lee D D. Algorithms for non-negative matrix factorization[J]. Advances in Neural Information Processing Systems, 2015, 13(6):556-562.[4] Mcauley J, Leskovec J. Hidden factors and hidden topics:Understanding rating dimensions with review text[C]//ACM Conference on Recommender Systems. Hong Kong, China:ACM, 2013:165-172.[5] Almahairi A, Kastner K, Cho K, et al. Learning distributed representations from reviews for collaborative filtering[C]//Proceedings of the 9th ACM Conference on Recommender Systems. Vienna, Austria:ACM, 2015:147-154.[6] Sang S L, Chung T, Mcleod D. Dynamic item recommendation by topic modeling for social networks[C]//Eighth International Conference on Information Technology:New Generations. Las Vegas, NV, USA:IEEE, 2011:884-889.[7] Bao Y, Fang H, Zhang J. TopicMF:Simultaneously exploiting ratings and reviews for recommendation[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence. Quebec, Canada:AAAI, 2014:2-8.[8] Blei D M, Ng A Y. Latent dirchlet allocation[J]. Journal of Machine Learning Research, 2003, 3(1):993-1022.[9] Almahairi A, Kastner K, Cho K, et al. Learning distributed representations from reviews for collaborative filtering[C]//Proceedings of the 9th ACM Conference on Recommender Systems. Vienna, Austria:ACM, 2015:147-154.[10] Wang C, Blei D M. Collaborative topic modeling for recommending scientific articles[C]//Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY, USA:ACM, 2011:448-456.[11] Lawrence S, Giles C L, Tsoi A C, et al. Face recognition:A convolutional neural-network approach[J]. IEEE Transactions on Neural Networks, 1997, 8(1):98-113.[12] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. (2015-04-10). http://arxiv.org/abs/1409.1556.[13] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA:IEEE, 2015:1-9.[14] Graves A. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.[15] Graves A. Supervised sequence labelling with recurrent neural networks[J]. Studies in Computational Intelligence, 2012, 385:1-124.[16] Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks[J]. Advances in Neural Information Processing Systems, 2014, 4:3104-3112.[17] 陈达. 基于深度学习的推荐系统研究[D]. 北京:北京邮电大学, 2014.CHEN Da. Analysis on Deep Learning Based Recommendation System[D]. Beijing:Beijing University of Posts and Telecommunications, 2014.(in Chinese)[18] 杨宇. 基于深度学习特征的图像推荐系统[D]. 成都:电子科技大学, 2015.YANG Yu. Image Recommendation System Based on Deep Learning[D]. Chengdu:University of Electronic Science and Technology of China, 2015.(in Chinese)[19] Wang H, Wang N, Yeung D Y. Collaborative deep learning for recommender systems[C]//Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY, USA:ACM, 2014:1235-1244.[20] Vincent P, Larochelle H, Lajoie I, et al. Stacked denoising autoencoders:Learning useful representations in a deep network with a local denoising criterion.[J]. Journal of Machine Learning Research, 2010, 11(6):3371-3408.

PDF(1022 KB)

Accesses

Citation

Detail

段落导航

收稿日期	出版日期
2016-12-13	2017-10-15
发布日期
2017-10-15

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

访问统计

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

访问统计