[논문]Conditional Generative Adversarial Network(CGAN) 기반 협업 필터링 추천 시스템

강소이; 신경식

doi:10.13088/jiis.2021.27.3.157

Conditional Generative Adversarial Network(CGAN) 기반 협업 필터링 추천 시스템
Conditional Generative Adversarial Network based Collaborative Filtering Recommendation System 원문보기

지능정보연구 = Journal of intelligence and information systems, v.27 no.3, 2021년, pp.157 - 173

강소이 (이화여자대학교 일반대학원 빅데이터분석학) , 신경식 (이화여자대학교 경영대학)

초록
AI-Helper

소비자의 욕구와 관심에 맞추어 개인화된 제품을 추천하는 추천 시스템은 비즈니스에 필수적인 기술로서의 그 중요성이 증가하고 있다. 추천 시스템의 대표적인 모형 중 협업 필터링은 우수한 성능으로 다양한 분야에서 활용되고 있다. 그러나 협업필터링은 사용자-아이템의 선호도 정보가 충분하지 않을 경우 성능이 저하되는 희소성의 문제가 있다. 또한 실제 평점 데이터의 경우 대부분 높은 점수에 데이터가 편향되어 있어 심한 불균형을 갖는다. 불균형 데이터에 협업 필터링을 적용할 경우 편향된 클래스에 과도하게 학습되어 추천 성능이 저하된다. 이러한 문제를 해결하기 위해 많은 선행연구들이 진행되어 왔지만 추가적인 외부 데이터 또는 기존의 전통적인 오버샘플링 기법에 의존한 추천을 시도하였기에 유용성이 떨어지고 추천 성능 측면에서 한계점이 있었다. 본 연구에서는 CGAN을 기반으로 협업 필터링 구현 시 발생하는 희소성 문제를 해결함과 동시에 실제 데이터에서 발생하는 데이터 불균형을 완화하여 추천의 성능을 높이는 것을 목표로 한다. CGAN을 이용하여 비어있는 사용자-아이템 매트릭스에 실제와 흡사한 가상의 데이터를 생성하여, 희소성을 가지고 있는 기존의 매트릭스로만 학습한 것과 비교했을 때 높은 정확도가 예상된다. 이 과정에서 Condition vector y를 이용하여 소수 클래스에 대한 분포를 파악하고 그 특징을 반영하여 데이터를 생성하였다. 이후 협업 필터링을 적용하고, 하이퍼파라미터 튜닝을 통해 추천 시스템의 성능을 최대화하는데 기여하였다. 비교 대상으로는 전통적인 오버샘플링 기법인 SMOTE, BorderlineSMOTE, SVM-SMOTE, ADASYN와 GAN을 사용하였다. 결과적으로 데이터 희소성을 가지고 있는 기존의 실제 데이터뿐만 아니라 기존 오버샘플링 기법들보다 제안 모형의 추천 성능이 우수함을 확인하였으며, RMSE, MAE 평가 척도에서 가장 높은 예측 정확도를 나타낸다는 사실을 증명하였다.

Abstract ▼ AI-Helper

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE e

주제어

표/그림 (6)

그림 MovieLens distribution of rating
표 MovieLens 100K data
그림 Basic structure
표 Hyperparameter array list
그림 Example of datasets before and after oversampling
표 Comparison of RMSE, MAE

참고문헌 (32)

B. Vega-Marquez, C. Rubio-Escudero, J. C. Riquelme, and I. Nepomuceno-Chamorro, "Creation of synthetic data with conditional generative adversarial networks," International Workshop on Soft Computing Models in Industrial and Environmental Applications, (2019), 231~240.
Chevalier, J. and Mayzlin, D, "The effect of word of mouth on sales: Online book reviews," J. of Marketing Research, 43(2006), 3.
D. Billsus and M. . Pazzani, "Learning collaborative information filters," Proceedings of the Fifteenth International Conference on Machine Learning, Vol. 54(1998), 48.
Douzas, G., & Bacao, F, "Effective data generation for imbalanced learning using conditional generative adversarial networks," Expert Systems with Applications, 91(2017), 464~471.

상세보기
Fiore, U., A. D. Santis, F. Perla, P. Zanetti, and F. Palmieri, "Using generative adversarial networks for improving classification effectiveness in credit card fraud detection," Information Sciences, 479(2017), 448~455.

상세보기
G. Adomavicius, A. Tuzhilin, "Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions," IEEE Transactions on Knowledge and Data Engineering, 17(2005), 734~749.

상세보기
Goldberg, D., Nichols, D., Oki, B. M., and Terry, D, "Using collaborative filterin g to weave an information tapestry," Communications of the ACM, 35(12) (1992), 61-70.

상세보기
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D.,Ozair, S., Courville, A., & Bengio., Y, "Generative Adversarial Nets," Advances in neural information processing systems, (2014), 2672~2680.
H. Han, W. Y. Wang, and B. H. Mao, "Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning," Proceedings of the International Conference on Intelligent Computing, Berlin(2005), 878~887.
H. He, Y. Bai, E. A. Garcia and S. Li, "ADASYN: Adaptive synthetic sampling approach for imbalanced learning," Proc. IEEE Int. Joint Conf. Neural Netw. IEEE World Congr. Comput. Intell.(2008), 1322~1328.
H. M. Nguyen, E. W. Cooper, K. Kamei, "Borderline over-sampling for imbalanced data classification," International Journal of Knowledge Engineering and Soft Data Paradigms, 3(1)(2009), 4~21.
Kim, Chae, Kim, "Generating and Visualizing Neighbors of Cold-start Users in Recommender System," Journal of the Korea Institute of Information and Communication Engineering, (2019), 134~135.
Krawczyk B, "Learning from imbalanced data: open challenges and future directions," Progr. AI, 5 (4) (2016), 221~232.
Kwon, Hong, "Method to Improve Data Sparsity Problem of Collaborative Filtering Using Latent Attribute Preference," Journal of Internet Computing and Services, Vol.14, No.5(2013), 59~67.

원문보기 상세보기
Lee Y, Kim SW, Park S, Xie X, "How to impute missing ratings? Claims, solution, and its application to collaborative filtering," In: Proceedings of the 2018 World Wide Web conference on World Wide Web(2018), 783~792.
Lee, Kim, "Analysis of Data Imputation in Recommender Systems," Journal of KIISE, Vol. 44, No. 12(2017), 1333~1337.

원문보기 상세보기
Lu, L., Medo, M., Yeung, C. H., Zhang, Y. C., Zhang, Z. K., & Zhou, T, "Recommender systems," Physics Reports, 519(1) (2012), 1~49.

상세보기
M. K. Najafabadi, M. N. Mahrin, S. Chuprat, and H. M. Sarkan, "Improving the accuracy of collaborative filtering recommendations using clustering and association rules mining on implicit data," Comput. Hum. Behav, Vol. 67(2017), 113~128.

상세보기
Michal Koziarski, Michal Wozniak, Bartosz Krawczyk, "Combined Cleaning and Resampling algorithm for multi-class imbalanced data with label noise," Knowl.-Based Syst, Vol 204(2020), 106223.

상세보기
Mirza, M. and Osindero, S, "Conditional Generative Adversarial Nets," arXiv preprint arXiv:1411.1784, (2014).
N. Hu, J. Zhang, and P. A. Pavlou. "Overcoming the J-shaped Distribution of Product Reviews," Communications of the ACM, Vol. 52, No. 10(2009), 144~147.

상세보기
N. V. Chawla, et al, "SMOTE: synthetic minority over-sampling technique," Journal of Artificial Intelligence Research, Vol.16(2002), 321~357.

상세보기
P. Melville, R. J. Mooney, and R. Nagarajan, "Content-Boosted Collaborative Filtering for Improved Recommendations," American Association for Artificial Intelligence (www.aaai.org) (2002), 187-192.
R. Ghorbani and R. Ghousi, "Comparing different resampling methods in predicting Students' performance using machine learning techniques," IEEE Access, Vol. 8(2020), 67899~67911.

상세보기
R. Jin and J. Zhang, "Multi-class learning by smoothed boosting", Mach. Learn., Vol. 67, No. 3(2007), 207~227.

상세보기
Schoenmueller, V., Netzer, O., & Stahl, F, "The extreme distribution of online reviews: Prevalence, drivers and implications," Columbia Business School Research Paper(2018), No. 18~10.
Seo, Jeon, Lee, Jung, Kim, "An Over-sampling Method based on Generative Adversarial Networks for Effective Classification of Imbalanced Big Data," Journal of the Korea Institute of Information and Communication Engineering(2017), 1030~1032.
Shinhyun Ahn and Chung-Kon Shi, "Exploring Movie Recommendation System Using Cultural Metadata," Transactions on Edutainment II, Lecture Notes in Computer Science, Vol. 5660(2009), 119~134.
Son, Kim, Kim, Cho, "Review and Analysis of Recommender Systems," Journal of the Korean Institute of Industrial Engineers, 41(2) (2015), 185~208.

원문보기 상세보기
SongJie Gong, HongWu Ye, "An item based collaborative filtering using BP Neural Networks prediction," International Conference on Industrial and Information Systems(2009), 146~148.
Z.-H. Zhou and X.-Y. Liu, "Training cost-sensitive neural networks with methods addressing the class imbalance problem," IEEE Trans. Knowl. Data Eng., Vol. 18, No. 1(2006), 63~77.

상세보기
Zhang, C. X., Yang, M., Lv, J., & Wang, W. Q, "An improved hybrid collaborative filtering algorithm based on tags and time factor," Big Data Mining and Analytics, 1(2018), 48~56.

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증