순차적 추천에서의 RNN, CNN 및 GAN 모델 비교 연구 = A Comparison Study of RNN, CNN, and GAN Models in Sequential Recommendation

다국어 초록 (Multilingual Abstract)

Recently, the recommender system has been widely used in various fields such as movies, music, online shopping, and social media, and in the meantime, the recommender model has been developed from correlation analysis through the Apriori model, which can be said to be the first-generation model in the recommender system field. In 2005, many models have been proposed, including deep learning-based models, which are receiving a lot of attention within the recommender model. The recommender model can be classified into a collaborative filtering method, a content-based method, and a hybrid method that uses these two methods integrally. However, these basic methods are gradually losing their status as methodologies in the field as they fail to adapt to internal and external changing factors such as the rapidly changing user-item interaction and the development of big data. On the other hand, the importance of deep learning methodologies in recommender systems is increasing because of its advantages such as nonlinear transformation, representation learning, sequence modeling, and flexibility. In this paper, among deep learning methodologies, RNN, CNN, and GAN-based models suitable for sequential modeling that can accurately and flexibly analyze user-item interactions are classified, compared, and analyzed.

국문 초록 (Abstract)

최근 추천 시스템은 영화, 음악, 온라인 쇼핑 및 SNS 등 다양한 분야들에서 광범위하게 활용되고 있으며, 추천 시스템 분야에서 1세대 모델이라고 할수 있는 Apriori 모델을 통한 연관분석부터 최근 많은 주목을 받는 딥러닝 기반 모델들까지 많은 모델들이 제안되어왔다. 추천 시스템에서 기본 모델들은 협업 필터링(Collaborative filtering) 방법, 콘텐츠 기반 필터링(Content-based filtering) 방법, 그리고 이 두 방법을 통합적으로 사용하는 하이브리드 필터링(Hybrid filtering) 방법으로 분류될 수 있다. 하지만 이러한 모델들은 최근 점점 빠르게 변화하는 사용자-아이템 간의 상호관계와 빅데이터의 발전과 같은 내외 변화 요인들에 적응하지 못하면서 점점 분야 내 방법론으로써의 지위를 잃어가고 있다. 반면, 추천 시스템 내에서 딥러닝 기반 모델들은 비선형 변환, 표현학습, 순차적 모델링, 그리고 유연성과 같은 장점들 때문에 그 비중이 높아지고 있는 추세이다. 본 논문에서는 딥러닝 기반 추천 모델들 중에서도 사용자-아이템 간의 상호작용에 대해 보다 정확하고, 유연성 있게 분석이 가능한 순차적 모델링에 적합한 순환 신경망, 합성곱 신경망, 그리고 생성적 적대 신경망 중심 기반 모델로 분류하여 비교 및 분석한다.

참고문헌 (Reference)

• 1 M. Bubashait, "Urban Sound Classification Using DNN, CNN & LSTM a Comparative Approach" 46-50, 2021
• 2 Shu Wu, "Session-based Recommendation with Graph Neural Networks" 33 : 346-353, 2019
• 3 Shoujin Wang, "Sequential recommender systems : challenges, progress and prospects" 6332-6338, 2019
• 4 Ruiyang Ren, "Sequential Recommendation with Self-Attentive Multi-Adversarial Network" 89-98, 2020
• 5 W. Kang, "Self-Attentive Sequential Recommendation" 197-206, 2018
• 6 Yoshua Bengio, "Representation Learning : A Review and New Perspectives" 35 (35): 1798-1828, 2013
• 7 Aminu Da’u, "Recommendation system based on deep learning methods : a systematic review and new directions" 53 : 2709-2748, 2020
• 8 Homanga Bharadhwaj, "RecGAN : recurrent generative adversarial networks for recommendation systems" 372-376, 2018
• 9 Jiaxi Tang, "Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding" 565-573, 2018
• 10 Kan Ren, "Lifelong sequential modeling with personalized memorization for user response prediction" 565-574, 2019
• 11 Zhengwei Wang, "Generative Adversarial Networks in Computer vision : A Survey and Taxonomy" 54 (54): 1-38, 2022
• 12 Q. Liu, "EE 16th International Conference on Data Mining(ICDM), pp" 1053-1058, 2016
• 13 Hui Fang, "Deep Learning for Sequential Recommendation : Algorithms, Influential Factors, and Evaluations" 39 (39): 1-42, 2020
• 14 Shuai Zhang, "Deep Learning Based Recommender System : A Survey and New Perspectives" 52 (52): 1-38, 2019
• 15 Fei Sun, "BERT4Rec : Sequential Recommendation with Bidirectional Encoder Representations from Transformer" 1441-1450, 2019
• 16 Pengyu Zhao, "Adversarial Oracular Seq2seq Learning for Sequential Recommendation" 1905-1911, 2020
• 17 Shoujin Wang, "A survey on session-based recommender systems" 54 (54): 1-38, 2022
• 18 Yashar Deldjoo, "A survey on Adversarial Recommender Systems : from Attack/Defense strategies to Generative Adversarial Networks" 54 (54): 1-38, 2022
• 19 Feng Yu, "A dynamic recurrent model for next basket recommendation" 729-732, 2016
• 20 N. Chowdhury, "A comparative analysis of Feed-forward neural network & Recurrent Neural network to detect intrusion" 488-492, 2008
• 21 Le Wu, "A Survey on Accuracy-oriented Neural Recommendation : From Collaborative Filtering to Information-rich Recommendation" 1-20, 2021
• 22 R. Mu, "A Survey of Recommender Systems Based on Deep Learning" 6 : 69009-69022, 2018
• 23 Fajie Yuan, "A Simple Convolutional Generative Network forNext Item Recommendation" 582-590, 2019
• 24 Trinh Xuan Tuan, "3D Convolutional Networks for Session-based Recommendation with Content Features" 138-146, 2017