一种基于深度学习的混合推荐算法
|
摘要
推荐系统在电子商务的发展中发挥着越来越重要的作用,但用户对物品评分数据的稀疏性往往是推荐精度较低的重要原因。目前通常采用推荐技术对辅助信息进行处理,以缓解用户评价的稀疏性,并提高预测评分精度。通过相关模型,可以利用文本数据来提取物品的隐藏特征。最近,深度学习算法快速发展,因此文中选用了一种具有强大特征提取能力的新型深度网络架构——变分自编码器(Variational AutoEncoder,VAE)。通过将无监督变分自编码融合到概率矩阵分解(Probability Matrix Factorization,PMF)中,构建了一种感知上下文的新型推荐模型——变分矩阵分解(Variational AutoEncoder Matrix Factorization,VAEMF)。首先使用TD-IDF对物品的评价文档进行数据预处理,然后对处理后的数据使用VAE捕获物品的上下文信息特征,最后使用概率矩阵分解进一步提高预测评分精度。在两个真实数据集上的实验结果验证了所提方法相较于自编码算法及概率矩阵分解算法的优势。
Recommendation system is playing an increasingly indispensable role in the development of e-commerce,but the sparsity of user's rating data for the items in the recommendation system is often an important reason for the low recommendation accuracy.At present,the recommendation technology is usually used to process the auxiliary information to alleviate the sparsity of the user evaluation and improve the accuracy of the prediction score.Text data can be used to extract the hidden features of the item through related models.In recent years,the deep learning algorithm has developed rapidly.Therefore,this paper chose a variational autoencoder(VAE),which is a new type of network structure with powerful feature extraction capabilities.This paper proposed a novel context-aware recommendation model integrating the unsupervised method VAE into the variable matrix factorization(VAEMF)in the probability matrix factorization(PMF).Firstly,TD-IDF is used to preprocess the evaluation documents of the item.Then,the VAE is utilized to capture the context information features of the item.Finally,the probability matrix factorization is used to improve the accuracy of the prediction score.The experimental results on two real data sets show that this method is superior to the autoencoder and the probability matrix factorization recommendation methods.
Recommendation system is playing an increasingly indispensable role in the development of e-commerce,but the sparsity of user's rating data for the items in the recommendation system is often an important reason for the low recommendation accuracy.At present,the recommendation technology is usually used to process the auxiliary information to alleviate the sparsity of the user evaluation and improve the accuracy of the prediction score.Text data can be used to extract the hidden features of the item through related models.In recent years,the deep learning algorithm has developed rapidly.Therefore,this paper chose a variational autoencoder(VAE),which is a new type of network structure with powerful feature extraction capabilities.This paper proposed a novel context-aware recommendation model integrating the unsupervised method VAE into the variable matrix factorization(VAEMF)in the probability matrix factorization(PMF).Firstly,TD-IDF is used to preprocess the evaluation documents of the item.Then,the VAE is utilized to capture the context information features of the item.Finally,the probability matrix factorization is used to improve the accuracy of the prediction score.The experimental results on two real data sets show that this method is superior to the autoencoder and the probability matrix factorization recommendation methods.
引文
[1]YANG B,ZHAO P F.Recommended algorithm review[J].Journal of Shanxi University(Natural Science Edition),2011,34(3):337-350.(in Chinese)杨博,赵鹏飞.推荐算法综述[J].山西大学学报(自然科学版),2011,34(3):337-350.
[2]SHI Y,LARSON M,HANJALIC A.Collaborative filtering beyond the user-item matrix:A survey of the state of the art and future challenges[J].ACM Computing Surveys(CSUR),2014,47(1):1-45.
[3]MNIH A,SALAKHUTDINOV R R.Probabilistic matrix factorization[C]∥Advances in Neural Information Processing ystems 20(NIPS 2007).2008:1257-1264.
[4]LANG K.Newsweeder:Learning to filter netnews[C]∥Machine Learning Proceedings.1995:331-339.
[5]KOREN Y,BELL R,VOLINSKY C.Matrix factorization techniques for recommender systems[J].Computer,2009,42(8):30-37.
[6]SHI Y,LARSON M,HANJALIC A.Collaborative filtering beyond the user-item matrix:A survey of the state of the art and future challenges[J].ACM Computing Surveys(CSUR),2014,47(1):3.
[7]SUN Z J,XUE L,XU Y M,et al.Review of deep learning research[J].Application Research of Computers,2012,29(8):2806-2810.(in Chinese)孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810.
[8]SALAKHUTDINOV R,MNIH A,HINTON G.Restricted Boltzmann machines for collaborative filtering[C]∥Proceedings of the 24th International Conference on Machine Learning.ACM,2007:791-798.
[9]CHILIGUANO P,FAZEKAS G.Hybrid music recommender using content-based and social information[C]∥2016IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).IEEE,2016:2618-2622.
[10]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.ACM,2016:233-240.
[11]WANG H Y,DONG M W.Latent group recommendation based on dynamic probabilistic matrix factorization model integrated with CNN[J].Journal of Computer Research and Development,2017,54(8):1853-1863.(in Chinese)王海艳,董茂伟.基于动态卷积概率矩阵分解的潜在群组推荐[J].计算机研究与发展,2017,54(8):1853-1863.
[12]ADOMAVICIUS G,TUZHILIN A.Toward the next generation of recommender systems:A survey of the state-of-the-art and possible extensions[J].IEEE Transactions on Knowledge and Data Engineering,2005,17(6):734-749.
[13]D’ADDIO R M,MANZATO M G.A sentiment-based item description approach for kNN collaborative filtering[C]∥Proceedings of the 30th Annual ACM Symposium on Applied Computing.ACM,2015:1060-1065.
[14]POLAT H,DU W.SVD-based collaborative filtering with privacy[C]∥Proceedings of the 2005ACM Symposium on Applied Computing.ACM,2005:791-795.
[15]SALAKHUTDINOV R,MNIH A.Bayesian probabilistic matrix factorization using Markov chain Monte Carlo[C]∥Proceedings of the 25th International Conference on Machine Learning.ACM,2008:880-887.
[16]LI J,BIOUCAS-DIAS J M,PLAZA A.Collaborative nonnegative matrix factorization for remotely sensed hyperspectral unmixing[C]∥2012IEEE International Geoscience and Remote Sensing Symposium(IGARSS).IEEE,2012:3078-3081.
[17]BALDI P.Autoencoders,unsupervised learning,and deep architectures[C]∥Proceedings of ICML Workshop on Unsupervised and Transfer Learning.JMLR.org,2012:37-49.
[18]KINGMA D P,WELLING M.Auto-encoding variational bayes[J].arXiv preprint arXiv:1312.6114,2013.
[19]SEDHAIN S,MENON A K,SANNER S,et al.Autorec:Autoencoders meet collaborative filtering[C]∥Proceedings of the24th International Conference on World Wide Web.ACM,2015:111-112.
[20]LI S,KAWALE J,FU Y.Deep collaborative filtering via marginalized denoising auto-encoder[C]∥Proceedings of the 24th ACM International on Conference on Information and Knowledge Management.ACM,2015.
[21]WANG H,SHI X,YEUNG D Y.Relational Stacked Denoising Autoencoder for Tag Recommendation[C]∥Twenty-Ninth AAAI Conference on Artificial Intellgience.AAAI Press,2015:3052-3058.
[22]WANG C,BLEI D M.Collaborative topic modeling for recommending scientific articles[C]∥Proceedings of the 17th ACMSIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2011:448-456.
[23]WANG H,WANG N,YEUNG D Y.Collaborative deep learning for recommender systems[C]∥Proceedings of the 21th ACMSIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2015:1235-1244.
[2]SHI Y,LARSON M,HANJALIC A.Collaborative filtering beyond the user-item matrix:A survey of the state of the art and future challenges[J].ACM Computing Surveys(CSUR),2014,47(1):1-45.
[3]MNIH A,SALAKHUTDINOV R R.Probabilistic matrix factorization[C]∥Advances in Neural Information Processing ystems 20(NIPS 2007).2008:1257-1264.
[4]LANG K.Newsweeder:Learning to filter netnews[C]∥Machine Learning Proceedings.1995:331-339.
[5]KOREN Y,BELL R,VOLINSKY C.Matrix factorization techniques for recommender systems[J].Computer,2009,42(8):30-37.
[6]SHI Y,LARSON M,HANJALIC A.Collaborative filtering beyond the user-item matrix:A survey of the state of the art and future challenges[J].ACM Computing Surveys(CSUR),2014,47(1):3.
[7]SUN Z J,XUE L,XU Y M,et al.Review of deep learning research[J].Application Research of Computers,2012,29(8):2806-2810.(in Chinese)孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810.
[8]SALAKHUTDINOV R,MNIH A,HINTON G.Restricted Boltzmann machines for collaborative filtering[C]∥Proceedings of the 24th International Conference on Machine Learning.ACM,2007:791-798.
[9]CHILIGUANO P,FAZEKAS G.Hybrid music recommender using content-based and social information[C]∥2016IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).IEEE,2016:2618-2622.
[10]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.ACM,2016:233-240.
[11]WANG H Y,DONG M W.Latent group recommendation based on dynamic probabilistic matrix factorization model integrated with CNN[J].Journal of Computer Research and Development,2017,54(8):1853-1863.(in Chinese)王海艳,董茂伟.基于动态卷积概率矩阵分解的潜在群组推荐[J].计算机研究与发展,2017,54(8):1853-1863.
[12]ADOMAVICIUS G,TUZHILIN A.Toward the next generation of recommender systems:A survey of the state-of-the-art and possible extensions[J].IEEE Transactions on Knowledge and Data Engineering,2005,17(6):734-749.
[13]D’ADDIO R M,MANZATO M G.A sentiment-based item description approach for kNN collaborative filtering[C]∥Proceedings of the 30th Annual ACM Symposium on Applied Computing.ACM,2015:1060-1065.
[14]POLAT H,DU W.SVD-based collaborative filtering with privacy[C]∥Proceedings of the 2005ACM Symposium on Applied Computing.ACM,2005:791-795.
[15]SALAKHUTDINOV R,MNIH A.Bayesian probabilistic matrix factorization using Markov chain Monte Carlo[C]∥Proceedings of the 25th International Conference on Machine Learning.ACM,2008:880-887.
[16]LI J,BIOUCAS-DIAS J M,PLAZA A.Collaborative nonnegative matrix factorization for remotely sensed hyperspectral unmixing[C]∥2012IEEE International Geoscience and Remote Sensing Symposium(IGARSS).IEEE,2012:3078-3081.
[17]BALDI P.Autoencoders,unsupervised learning,and deep architectures[C]∥Proceedings of ICML Workshop on Unsupervised and Transfer Learning.JMLR.org,2012:37-49.
[18]KINGMA D P,WELLING M.Auto-encoding variational bayes[J].arXiv preprint arXiv:1312.6114,2013.
[19]SEDHAIN S,MENON A K,SANNER S,et al.Autorec:Autoencoders meet collaborative filtering[C]∥Proceedings of the24th International Conference on World Wide Web.ACM,2015:111-112.
[20]LI S,KAWALE J,FU Y.Deep collaborative filtering via marginalized denoising auto-encoder[C]∥Proceedings of the 24th ACM International on Conference on Information and Knowledge Management.ACM,2015.
[21]WANG H,SHI X,YEUNG D Y.Relational Stacked Denoising Autoencoder for Tag Recommendation[C]∥Twenty-Ninth AAAI Conference on Artificial Intellgience.AAAI Press,2015:3052-3058.
[22]WANG C,BLEI D M.Collaborative topic modeling for recommending scientific articles[C]∥Proceedings of the 17th ACMSIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2011:448-456.
[23]WANG H,WANG N,YEUNG D Y.Collaborative deep learning for recommender systems[C]∥Proceedings of the 21th ACMSIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2015:1235-1244.