EDMF: Efficient Deep Matrix Factorization With Review Feature Learning for Industrial Recommender System
| العنوان: | EDMF: Efficient Deep Matrix Factorization With Review Feature Learning for Industrial Recommender System |
|---|---|
| المؤلفون: | Jiazhang Wang, Zhaoli Zhang, Chao Zheng, Xiaoxuan Shen, Hai Liu, Duantengchuan Li, Zhen Zhang, Neal N. Xiong, Ke Lin |
| المصدر: | IEEE Transactions on Industrial Informatics. 18:4361-4371 |
| بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2022. |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | Computer science, business.industry, Recommender system, Machine learning, computer.software_genre, Convolutional neural network, Computer Science Applications, Matrix decomposition, Interactivity, Control and Systems Engineering, Prior probability, Feature (machine learning), Maximum a posteriori estimation, Artificial intelligence, Electrical and Electronic Engineering, business, computer, Feature learning, Information Systems |
| الوصف: | Recommendation accuracy is a fundamental problem in the quality of the recommendation system. In this paper, we propose an efficient deep matrix factorization with review feature learning for the industrial recommender system (EDMF). Two characteristics in user's review are revealed. First, interactivity between the user and the item, which can also be considered as the former's scoring behavior on the latter, is exploited in a review. Second, the review is only a partial description of the user's preferences for the item, which is revealed as the sparsity property. Specifically, in the first characteristic, EDMF extracts the interactive features of onefold review by convolutional neural networks with word attention mechanism. Subsequently, L0 norm is leveraged to constrain the review considering that the review information is a sparse feature, which is the second characteristic. Furthermore, the loss function is constructed by maximum a posteriori estimation theory, where the interactivity and sparsity property are converted as two prior probability functions. Finally, the alternative minimization algorithm is introduced to optimize the loss functions. Experimental results on several datasets demonstrate that the proposed methods, which show good industrial conversion application prospects, outperform the state-of-the-art methods in terms of effectiveness and efficiency. |
| تدمد: | 1941-0050 1551-3203 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_________::2bea168576ab2645cba2f3a4ccb552edTest https://doi.org/10.1109/tii.2021.3128240Test |
| حقوق: | CLOSED |
| رقم الانضمام: | edsair.doi...........2bea168576ab2645cba2f3a4ccb552ed |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 19410050 15513203 |
|---|