KIISE Transactions on Computing Practices (정보과학회 컴퓨팅의 실제 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Improving on Matrix Factorization for Recommendation Systems by Using a Character-Level Convolutional Neural Network

문자 수준 컨볼루션 뉴럴 네트워크를 이용한 추천시스템에서의 행렬 분해법 개선

  • 손동희 (서울대학교 전기정보공학부) ;
  • 심규석 (서울대학교 전기정보공학부)
  • Received : 2017.10.11
  • Accepted : 2017.12.05
  • Published : 2018.02.15
⟨ Previous Next ⟩

Abstract

Recommendation systems are used to provide items of interests for users to maximize a company's profit. Matrix factorization is frequently used by recommendation systems, based on an incomplete user-item rating matrix. However, as the number of items and users increase, it becomes difficult to make accurate recommendations due to the sparsity of data. To overcome this drawback, the use of text data related to items was recently suggested for matrix factorization algorithms. Furthermore, a word-level convolutional neural network was shown to be effective in the process of extracting the word-level features from the text data among these kinds of matrix factorization algorithms. However, it involves a large number of parameters to learn in the word-level convolutional neural network. Thus, we propose a matrix factorization algorithm which utilizes a character-level convolutional neural network with which to extract the character-level features from the text data. We also conducted a performance study with real-life datasets to show the effectiveness of the proposed matrix factorization algorithm.

추천시스템은 기업의 매출을 최대화 하기 위해, 사용자에게 관심도가 높은 제품을 제공해준다. 행렬 분해법은 추천시스템에서 자주 사용되는 방법으로 불완전한 사용자-제품 평점 행렬을 기반으로 한다. 하지만 제품과 사용자의 수가 점점 많아지면서, 데이터의 희소성문제로 인해 정확한 추천이 힘들어졌다. 이러한 문제점을 극복하기 위해, 제품과 관련된 텍스트 데이터를 사용하는 행렬 분해법 알고리즘이 최근에 제시되었다. 이런 행렬 분해법 알고리즘 중, 단어 수준 컨볼루션 뉴럴 네트워크를 사용하는 방법이 단어수준 특징들을 추출하여 텍스트 데이터를 효과적으로 반영한다. 하지만 단어수준 컨볼루션 뉴럴 네트워크에서는 학습해야 하는 파라미터의 수가 많다는 문제점이 있다. 그러므로 본 논문에서는 텍스트 데이터로부터 문자 수준 특징들을 뽑아 내기 위해 문자 수준 컨볼루션 뉴럴 네트워크를 사용하는 행렬분해법을 제안한다. 또한 제안하는 행렬 분해법의 성능을 검증하기 위해 실제 데이터를 이용하여 실험을 진행하였다.

Keywords

Acknowledgement

Supported by : 정보통신기술진흥센터, 한국연구재단

References

  1. D Kim, C Park, J Oh, S Lee, and H Yu. "Convolutional matrix factorization for document contextaware recommendation," Proc. of the 10th ACM Conference on Recommender Systems. ACM, pp. 233-240, 2016.
  2. H Ruining, and J McAuley, "VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback," AAAI, pp. 144-150, 2016.
  3. F Zhang, NJ Yuan, D Lian, X Xie, and WY Ma. "Collaborative knowledge base embedding for recommender systems," Proc. of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp. 353-362, 2016.
  4. R. Salakhutdinov and A. Mnih, "Probabilistic matrix factorization," Advances in neural information processing systems, pp. 1257-1264, 2008.
  5. G Hwang, Z Liu, K Q. Weinberger and L Maaten, "Densely Connected Convolutional Networks," Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
  6. Y Kim, "Convolutional neural networks for sentence classification," arXiv preprint arXiv:1408.5882 (2014).
  7. L Zhao, M Huang, Z Yao, R Su, Y Jiang and X Zhu, "Semi-Supervised Multinomial Naive Bayes for Text Classification by Leveraging Word-Level Statistical Constraint," AAAI, pp. 2877-2884, 2016.
  8. X Zhang, J Zhao and Y LeCun, "Character-level convolutional networks for text classification," Advances in neural information processing systems, pp. 649-657, 2015.
  9. Y Shen, X He, J Gao, L Deng and G Mesnil, "A latent semantic model with convolutional-pooling structure for information retrieval," Proc. of the 23rd ACM International Conference on Conference on Information and Knowledge Management. ACM, pp. 101-110, 2014.
  10. J Pennington, R Socher and C Manning, "Glove: Global Vectors for Word Representation," Proc. of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 1532-1543, 2014.