ACMF:基于卷积注意力模型的评分预测研究

摘要
参考文献
相关文章 (15)

全文: PDF (2477 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要评分数据稀疏是影响评分预测的主要因素之一。为了解决数据稀疏问题,一些推荐模型利用辅助信息改善评分预测的准确率。然而大多数推荐模型缺乏对辅助信息的深入理解,因此还有很大的提升空间。鉴于卷积神经网络在特征提取方面和注意力机制在特征选择方面的突出表现,该文提出一种融合卷积注意力神经网络(Attention Convolutional Neural Network, ACNN)的概率矩阵分解模型: 基于卷积注意力的矩阵分解(Attention Convolutional Model based Matrix Factorization, ACMF),该模型首先使用词嵌入将高维、稀疏的词向量压缩成低维、稠密的特征向量;接着,通过局部注意力层和卷积层学习评论文档的特征;然后,利用用户和物品的潜在模型生成评分预测矩阵;最后计算评分矩阵的均方根误差。在ML-100k、ML-1m、ML-10m、Amazon数据集上的实验结果表明,与当前取得最好预测准确率的PHD模型相比,ACMF模型在预测准确率上分别提高了3.57%、1.25%、0.37%和0.16%。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	商齐
	曾碧卿
	王盛玉
	周才东
	曾锋

关键词 ：卷积神经网络, 注意力机制, 评分预测

Abstract：The sparseness of rating data is one of the main factors that affect the recommender models prediction. To exploit the advantage of convolutional neural networks in feature extraction and attention mechanism in feature selection, a probability matrix factorization model (PMF) with attention convolutional neural network(ACNN) is proposed as attention convolutional model based matrix factorization (ACMF). Firstly, the ACMF model compresses the high dimensional and sparse word vectors into low dimensional and dense feature vectors through word embedding technique. Then, it uses the local attention layer and convolutional layer to learn the feature of review document, and utilizes the user and item’s latent models to reconstruct the rating prediction matrix. Finally, the loss function is set as the root-mean-square error of rating matrix. Compared with the best prediction model PHD, the ACMF model increases the accuracy rate on ML-100k, ML-1m, ML-10m and Amazon datasets by 3.57%, 1.25%, 0.37% and 0.16%, respectively.

Key words： convolutional neural network attention mechanism rating prediction

收稿日期: 2018-01-31

中图分类号:

TP391

基金资助:国家自然科学基金(61503143);华南师范大学研究生创新计划项目(2016lkxm59)

作者简介: 商齐(1994—),硕士研究生,主要研究领域为自然语言处理、推荐系统。E-mail:1162276945@qq.com
曾碧卿(1969—),通信作者,博士,教授,主要研究领域为人工智能与自然语言处理。E-mail:zengbiqing0528@163.com
王盛玉(1992—),硕士研究生,主要研究领域为自然语言处理、情感分析。E-mail:wangshengyu_1992@163.com

链接本文:

http://jcip.cipsc.org.cn/CN/Y2018/V32/I11/86

[1] Herlocker J L,et al.Evaluating collaborative filtering recommender systems[J].ACM Transactions on Information Systems (TOIS),2004,22(1):5-53.
[2] 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.ACM,2011:448-456.
[3] Wang H,Wang N,Yeung D Y.Collaborative deep learning for recommender systems[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2015:1235-1244.
[4] McAuley J,Leskovec J.Hidden factors and hidden topics:Understanding rating dimensions with review text[C]//Proceedings of the 7th ACM Conference on Recommender Systems.ACM,2013:165-172.
[5] 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,2015:811-820.
[6] Ling G,Lyu M R,King I.Ratings meet reviews:A combined approach to recommend[C]//Proceedings of the 8th ACM Conference on Recommender Systems.ACM,2014:105-112.
[7] 马春平,陈文亮.基于评论主题分析的评分预测方法研究[J].中文信息学报,2017,31(2):204-211.
[8] Blei D M,Ng A Y,Jordan M I.Latent Dirichlet allocation[J].Journal of Machine Learning Research,2003,3(Jan):993-1022.
[9] Mnih A,Salakhutdinov R.Probabilistic matrix factorization[C]//Advances in Neural Information Processing Systems.2008:1257-1264.
[10] Dong X,et al.A hybrid collaborative filtering model with deep structure for recommender systems[C]//AAAI,2017:1309-1315.
[11] Liu J,Wang D,Ding Y.PHD:A probabilistic model of hybrid deep collaborative filtering for recommender systems[C]//Proceedings of the Ninth Asian Conference on Machine Learning,PMLR 77,2017:224-239.
[12] Seo S,et al.Interpretable convolutional neural networks with dual local and global attention for review rating prediction[C]//Eleventh ACM Conference on Recommender Systems.ACM,2017:297-305.
[13] Seo S,et al.Representation learning of users and items for review rating prediction using attention-based convolutional neural network[C]//3rd International Workshop on Machine Learning Methods for Recommender Systems (MLRec)(SDM’17),2017.
[14] Kim D,et al.Deep hybrid recommender systems via exploiting document context and statistics of items[J].Information Sciences,2017,417:72-87.
[15] Kim D,et al.Convolutional matrix factorization for document context-aware recommendation[C]//Proceedings of the 10th ACM Conference on Recommender Systems.ACM,2016:233-240.
[16] Koren Y.Factorization meets the neighborhood:A multifaceted collaborative filtering model[C]//Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2008:426-434.
[17] Xu K,et al.Show,attend and tell:Neural image caption generation with visual attention[C]//International Conference on Machine Learning,2015:2048-2057.
[18] Bahdanau D,Cho K,Bengio Y.Neural machine translation by jointly learning to align and translate[J].arXiv preprint arXiv:1409.0473,2014.
[19] Luong M T,Pham H,Manning C D.Effective approaches to attention-based neural machine translation[J].arXiv preprint arXiv:1508.04025,2015.
[20] Yin W,et al.ABCNN:Attention-based convolutional neural network for modeling sentence pairs[J].Computer Science,2015.
[21] Wang Y,et al.Attention-based LSTM for aspect-level sentiment classification[C]//Conference on Empirical Methods in Natural Language Processing,2016:606-615.
[22] Lécun Y,et al.Gradient-based learning applied to document recognition[C]//Proceedings of the IEEE,1998,86(11):2278-2324.
[23] Oord A V D,Dieleman S,Schrauwen B.Deep content-based music recommendation[J].Advances in Neural Information Processing Systems,2013(26):2643-2651.
[24] He R,Mcauley J.VBPR:Visual Bayesian personalized ranking from implicit feedback[C]//Thirtith AAAI Conference on Artificial Intelligence.AAAI Press,2016:144-150.
[25] Zhang F,et al.Collaborative knowledge base embedding for recommender Systems[C]//Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2016:353-362.
[26] Pennington J,Socher R,Manning C.Glove:Global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP),2014:1532-1543.
[27] Salakhutdinov R,Mnih A.Bayesian probabilistic matrix factorization using Markov chain Monte Carlo[C]//Proceedings of the International Conference on Machine Learning.ACM,2008:880-887.
[28] Zhang S,et al.Learning from incomplete ratings using non-negative matrix factorization[C]//Proceedings of the Siam International Conference on Data Mining,April 20-22,2006,Bethesda,Md,Usa.DBLP,2006:549-553.
[29] Sarwar B,et al.Application of dimensionality reduction in recommender systems[J].Acm Webkdd Workshop,2000.
[30] George T,Merugu S.A scalable collaborative Filtering framework based on co-clustering[C]//Proceedings of the IEEE International Conference on Data Mining.IEEE,2005:625-628.