基于改进CNN的局部相似性预测推荐模型
|
摘要
为缓解推荐系统中数据稀疏性问题,利用卷积神经网络CNN具有较强捕捉局部特征能力的优势,通过加入一个调节层,提出一种改进CNN的局部相似性预测推荐模型LSPCNN。新模型对初始用户-项目评分矩阵进行迭代调整,使用户兴趣偏好局部特征化,再融合CNN对缺失评分进行预测,从而实施个性化推荐。实验结果表明,LSPCNN模型在不同数据稀疏度下的MAE值较传统推荐方法平均下降4%,有效缓解了数据稀疏性,提高了推荐系统的性能。
In order to alleviate the problem of data sparsity in recommendation systems, based on the advantage of convolutional neural networks(CNNs) in capturing local features, we propose a local similarity prediction recommendation model based on improved CNN(LSPCNN) by adding an adjustment layer. The new model iteratively adjusts the initial user-item scoring matrix to localize user's interest preference. And then CNNs are integrated to predict the missing score and achieve personalized recommendation. Experimental results show that the MAE value of the LSPCNN model under different degrees of data sparsity decreases by an average of 4% compared with the traditional recommendation methods, and it effectively alleviates the data sparsity problem and improves the performance of recommendation systems.
In order to alleviate the problem of data sparsity in recommendation systems, based on the advantage of convolutional neural networks(CNNs) in capturing local features, we propose a local similarity prediction recommendation model based on improved CNN(LSPCNN) by adding an adjustment layer. The new model iteratively adjusts the initial user-item scoring matrix to localize user's interest preference. And then CNNs are integrated to predict the missing score and achieve personalized recommendation. Experimental results show that the MAE value of the LSPCNN model under different degrees of data sparsity decreases by an average of 4% compared with the traditional recommendation methods, and it effectively alleviates the data sparsity problem and improves the performance of recommendation systems.
引文
[1] Xu Hai-ling,Wu Xiao,Li Xiao-dong,et al.Comparison study of internet recommendation system[J].Journal of Software,2009,20(2):350-362.(in Chinese)
[2] Huang Z,Chen H,Zeng D.Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering[J].ACM Transactions on Information Systems,2004,22(1):116-142.
[3] Breese J S,Heckerman D,Kadie C.Empirical analysis of predictive algorithms for collaborative filtering[C]//Proc of the 14th Conference on Uncertainty in Artificial Intelligence,1998:43-52.
[4] Zhang Guang-wei,Li De-yi,Li Peng,et al.A collaborative filtering recommendation algorithm based on cloud model[J].Journal of Software,2007,18(10):2403-2411.(in Chinese)
[5] Zhao Liang,Hu Nai-jing,Zhang Shou-zhi.Algorithm design for personalization recommendation system[J].Journal of Computer Research and Development,2002,39(8):986-991.(in Chinese)
[6] Sarwar B,Karypis G,Konstan J,et al.Application of dimensionality reduction in recommender systems[C]//Proc of 2000 ACM WebKDD,2000:1.
[7] Xiong Zhong-yang,Liu Qin,Zhang Yu-fang,et al.Improved algorithm of collaborative filtering based on item classification[J].Application Research of Computers,2012,29(2):493-496.(in Chinese)
[8] Xiong Zhong-yang,Liu Qin,Zhang Yu-fang.Collaborative filtering recommendation algorithm based on item classification and cloud model[J].Application Research of Computers,2012,29(10):3660-3664.(in Chinese)
[9] Ren J,Zhou T,Zhang Y C.Information filtering via self-consistent refinement[J].EPL(Europhysics Letters),2008,82(5):58007.
[10] Sun D,Zhou T,Liu J G,et al.Information filtering based on transferring similarity[J].Physical Review,Statistical,Nonlinear,and Soft Matter Physics,2009,80(1):017101.
[11] Chua L O,Roska T.CNN paradigm[J].IEEE Transactions on Circuits & Systems I Fundamental Theory & Applications,1993,40(3):147-156.
[12] Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[C]//Proc of International Conference on Neural Information Processing Systems,2012:1097-1105.
[13] Abdel-Hamid O,Mohamed A R,Jiang H,et al.Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition[C]//Proc of IEEE International Conference on Acoustics,Speech and Signal Processing,2012:4277-4280.
[14] Cai Guo-yong,Xia Bin-bin.Multimedia sentiment analysis based on convolutional neural network[J].Journal of Computer Applications,2016,36(2):428-431.(in Chinese)
[15] Lian Xu-bao.The research on recommendation algorithm based on learning to rank and convolutional neural network [D].Dalian:Dalian University of Technology,2016.(in Chinese)
[16] Wu xi.Recommendation algorithm based on convolution neural network[D].Guangzhou:South China University of Technology,2016.(in Chinese)
[17] Gong Y,Zhang Q.Hashtag recommendation using attention-based convolutional neural network[C]//Proc of the 25th International Joint Conference on Artificial Intelligence,2016:2782-2788.
[18] Seo S,Huang J,Yang H,et al.Representation learning of users and items for review rating prediction using attention-based convolutional neural network[C]//Proc of the 3rd International Workshop on Machine Learning Methods for Recommender Systems(SDM’17),2017:297-305.
[19] Wang X,Yu L,Ren K,et al.Dynamic attention deep model for article recommendation by learning human editors’ demonstration[C]//Proc of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2017:2051-2059.
[20] Li Si-qin,Lin Lei,Sun Cheng-jie.Click-through rate prediction for search advertising based on convolution neural network[J].Intelligent Computer and Applications,2015(5):22-25.(in Chinese)
[21] Nair V,Hinton G E.Rectified linear units improve restricted Boltzmann machines[C]//Proc of International Conference on International Conference on Machine Learning,2010:807-814.
[22] Wang Duo-min,Liu Shu-fen.LogReLU:A new rectified activation unit using log funcion[J].Journal of Jilin University(Science Edition),2017,55(3):617-622.(in Chinese)
[23] Chen Yi.Frequently-used prediction method and evaluation summary[J].Journal of Sichuan Normal University(Natural Science),2002,25(1):70-73.(in Chinese)
[1] 许海玲,吴潇,李晓东,等.互联网推荐系统比较研究[J].软件学报,2009,20(2):350-362.
[4] 张光卫,李德毅,李鹏,等.基于云模型的协同过滤推荐算法[J].软件学报,2007,18(10):2403-2411.
[5] 赵亮,胡乃静,张守志.个性化推荐算法设计[J].计算机研究与发展,2002,39(8):986-991.
[7] 熊忠阳,刘芹,张玉芳,等.基于项目分类的协同过滤改进算法[J].计算机应用研究,2012,29(2):493-496.
[8] 熊忠阳,刘芹,张玉芳.结合项目分类和云模型的协同过滤推荐算法[J].计算机应用研究,2012,29(10):3660-3664.
[14] 蔡国永,夏彬彬.基于卷积神经网络的图文融合媒体情感预测[J].计算机应用,2016,36(2):428-431.
[15] 练绪宝.基于排序学习和卷积神经网络的推荐算法研究[D].大连:大连理工大学,2016.
[16] 吴浠.基于卷积神经网络的推荐算法[D].广州:华南理工大学,2016.
[20] 李思琴,林磊,孙承杰.基于卷积神经网络的搜索广告点击率预测[J].智能计算机与应用,2015(5):22-25.
[22] 王多民,刘淑芬.一种使用log函数的新型修正激活单元LogReLU[J].吉林大学学报(理学版),2017,55(3):617-622.
[23] 程昳.常用预测方法及评价综述[J].四川师范大学学报(自然科学版),2002,25(1):70-73.
[2] Huang Z,Chen H,Zeng D.Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering[J].ACM Transactions on Information Systems,2004,22(1):116-142.
[3] Breese J S,Heckerman D,Kadie C.Empirical analysis of predictive algorithms for collaborative filtering[C]//Proc of the 14th Conference on Uncertainty in Artificial Intelligence,1998:43-52.
[4] Zhang Guang-wei,Li De-yi,Li Peng,et al.A collaborative filtering recommendation algorithm based on cloud model[J].Journal of Software,2007,18(10):2403-2411.(in Chinese)
[5] Zhao Liang,Hu Nai-jing,Zhang Shou-zhi.Algorithm design for personalization recommendation system[J].Journal of Computer Research and Development,2002,39(8):986-991.(in Chinese)
[6] Sarwar B,Karypis G,Konstan J,et al.Application of dimensionality reduction in recommender systems[C]//Proc of 2000 ACM WebKDD,2000:1.
[7] Xiong Zhong-yang,Liu Qin,Zhang Yu-fang,et al.Improved algorithm of collaborative filtering based on item classification[J].Application Research of Computers,2012,29(2):493-496.(in Chinese)
[8] Xiong Zhong-yang,Liu Qin,Zhang Yu-fang.Collaborative filtering recommendation algorithm based on item classification and cloud model[J].Application Research of Computers,2012,29(10):3660-3664.(in Chinese)
[9] Ren J,Zhou T,Zhang Y C.Information filtering via self-consistent refinement[J].EPL(Europhysics Letters),2008,82(5):58007.
[10] Sun D,Zhou T,Liu J G,et al.Information filtering based on transferring similarity[J].Physical Review,Statistical,Nonlinear,and Soft Matter Physics,2009,80(1):017101.
[11] Chua L O,Roska T.CNN paradigm[J].IEEE Transactions on Circuits & Systems I Fundamental Theory & Applications,1993,40(3):147-156.
[12] Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[C]//Proc of International Conference on Neural Information Processing Systems,2012:1097-1105.
[13] Abdel-Hamid O,Mohamed A R,Jiang H,et al.Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition[C]//Proc of IEEE International Conference on Acoustics,Speech and Signal Processing,2012:4277-4280.
[14] Cai Guo-yong,Xia Bin-bin.Multimedia sentiment analysis based on convolutional neural network[J].Journal of Computer Applications,2016,36(2):428-431.(in Chinese)
[15] Lian Xu-bao.The research on recommendation algorithm based on learning to rank and convolutional neural network [D].Dalian:Dalian University of Technology,2016.(in Chinese)
[16] Wu xi.Recommendation algorithm based on convolution neural network[D].Guangzhou:South China University of Technology,2016.(in Chinese)
[17] Gong Y,Zhang Q.Hashtag recommendation using attention-based convolutional neural network[C]//Proc of the 25th International Joint Conference on Artificial Intelligence,2016:2782-2788.
[18] Seo S,Huang J,Yang H,et al.Representation learning of users and items for review rating prediction using attention-based convolutional neural network[C]//Proc of the 3rd International Workshop on Machine Learning Methods for Recommender Systems(SDM’17),2017:297-305.
[19] Wang X,Yu L,Ren K,et al.Dynamic attention deep model for article recommendation by learning human editors’ demonstration[C]//Proc of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2017:2051-2059.
[20] Li Si-qin,Lin Lei,Sun Cheng-jie.Click-through rate prediction for search advertising based on convolution neural network[J].Intelligent Computer and Applications,2015(5):22-25.(in Chinese)
[21] Nair V,Hinton G E.Rectified linear units improve restricted Boltzmann machines[C]//Proc of International Conference on International Conference on Machine Learning,2010:807-814.
[22] Wang Duo-min,Liu Shu-fen.LogReLU:A new rectified activation unit using log funcion[J].Journal of Jilin University(Science Edition),2017,55(3):617-622.(in Chinese)
[23] Chen Yi.Frequently-used prediction method and evaluation summary[J].Journal of Sichuan Normal University(Natural Science),2002,25(1):70-73.(in Chinese)
[1] 许海玲,吴潇,李晓东,等.互联网推荐系统比较研究[J].软件学报,2009,20(2):350-362.
[4] 张光卫,李德毅,李鹏,等.基于云模型的协同过滤推荐算法[J].软件学报,2007,18(10):2403-2411.
[5] 赵亮,胡乃静,张守志.个性化推荐算法设计[J].计算机研究与发展,2002,39(8):986-991.
[7] 熊忠阳,刘芹,张玉芳,等.基于项目分类的协同过滤改进算法[J].计算机应用研究,2012,29(2):493-496.
[8] 熊忠阳,刘芹,张玉芳.结合项目分类和云模型的协同过滤推荐算法[J].计算机应用研究,2012,29(10):3660-3664.
[14] 蔡国永,夏彬彬.基于卷积神经网络的图文融合媒体情感预测[J].计算机应用,2016,36(2):428-431.
[15] 练绪宝.基于排序学习和卷积神经网络的推荐算法研究[D].大连:大连理工大学,2016.
[16] 吴浠.基于卷积神经网络的推荐算法[D].广州:华南理工大学,2016.
[20] 李思琴,林磊,孙承杰.基于卷积神经网络的搜索广告点击率预测[J].智能计算机与应用,2015(5):22-25.
[22] 王多民,刘淑芬.一种使用log函数的新型修正激活单元LogReLU[J].吉林大学学报(理学版),2017,55(3):617-622.
[23] 程昳.常用预测方法及评价综述[J].四川师范大学学报(自然科学版),2002,25(1):70-73.