The Transactions of the Korea Information Processing Society (정보처리학회 논문지)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Study Comparing the Performance of Linear and Non-linear Models in Recommendation Systems

추천 시스템에서의 선형 모델과 비선형 모델의 성능 비교 연구

  • 성다훈 (숙명여자대학교 IT공학과) ;
  • 임유진 (숙명여자대학교 인공지능공학부)
  • Received : 2024.07.11
  • Accepted : 2024.07.22
  • Published : 2024.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Since recommendation systems play a key role in increasing the revenue of companies, various approaches and models have been studied in the past. However, this diversity also leads to a complexity in the types of recommendation systems, which makes it difficult to select a recommendation model. Therefore, this study aims to solve the difficulty of selecting an appropriate recommendation model for recommendation systems by providing a unified criterion for categorizing various recommendation models and comparing their performance in a unified environment. The experiments utilized MovieLens and Coursera datasets, and the performance of linear models(ADMM-SLIM, EASER, LightGCN) and non-linear models(Caser, BERT4Rec) were evaluated using HR@10 and NDCG@10 metrics. This study will provide researchers and practitioners with useful information for selecting the best model based on dataset characteristics and recommendation context.

추천 시스템은 기업의 매출 증가로 이어질 만큼 핵심적인 역할을 하기에 추천 시스템에 대한 연구는 과거부터 다양한 접근법과 모델들이 연구되어왔다. 그러나 이러한 다양성으로 인해 추천 시스템의 종류 또한 복잡하게 구성되고 있어 추천 모델을 선택하는 데 어려움이 따른다. 따라서 본 연구는 추천 시스템에서 적절한 추천 모델 선택의 어려움을 해결하고자, 다양한 추천 모델을 구분하는 통합적인 기준을 제공하고, 통일된 환경에서 이들의 성능을 비교 평가하였다. 실험은 MovieLens와 Coursera 데이터셋을 활용하였으며, 선형 모델(ADMM-SLIM, EASER, LightGCN)과 비선형 모델(Caser, BERT4Rec)을 HR@10과 NDCG@10 지표를 통해 성능을 평가하였다. 본 연구는 연구진과 실무자들에게 데이터셋 특성과 추천 상황에 맞는 최적의 모델을 선택하는 데 유용한 정보를 제공할 것이다.

Keywords

Acknowledgement

본 연구는 과학기술정보통신부 및 정보통신기획평가원의 ICT혁신인재 4.0사업의 연구결과로 수행되었음(IITP-2024-RS-2022-00156299).

References

  1. D.-H. Seong, and Y. Lim, "A study comparing the performance of Linear and deep learning models in recommender systems as a function of data size," Proceedings of the Annual Symposium of Korea Information Processing Society Conference (KIPS) 2024, Vol.31, pp.715-718, 2024. 
  2. Dataset of MovieLens, Grouplens [Internet], https://grouplens.org/datasets/movielens/. 
  3. Dataset of Coursera, Kaggle [Internet], https://www.kaggle.com/datasets/imuhammad/course-reviews-on-coursera. 
  4. H. Steck, M. Dimakopoulou, N. Riabov, and T. Jebara, "ADMM SLIM: Sparse recommendations for many users," in Proceedings of the 13th ACM International Conference on Web Search and Data Mining (WSDM '20), Feb. 3-7, 2020. 
  5. X. Ning and G. Karypis, "SLIM: Sparse linear methods for top-N recommender systems," in Proceedings of the IEEE International Conference on Data Mining(ICDM), pp.497-506, 2011. 
  6. S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein, "Distributed optimization and statistical learning via the alternating direction method of multipliers," Foundations and Trends® in Machine Learning, Vol.3, No.1, pp.1-122, 2011.  https://doi.org/10.1561/2200000016
  7. H. Steck and D. Liang, "Negative interactions for improved collaborative filtering: Don't go deeper, go higher," in Proceedings of the 15th ACM Conference on Recommender Systems (RecSys), pp.34-43, Sep. 27-Oct. 1, Amsterdam, Netherlands, 2021. 
  8. H. Steck, "Embarrassingly shallow autoencoders for sparse data," in Proceedings of the World Wide Web Conference (WWW), pp.3251-3257, May. 13-17, CA, USA, 2019. 
  9. X. He, K. Deng, X. Wang, Y. Li, Y. Zhang, and M. Wang, "LightGCN: Simplifying and powering graph convolution network for recommendation," in Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR '20), pp. 25-30, 2020. 
  10. N. T. Kipf and M. Welling, "Semi-supervised Classification with graph convolutional networks." in Proceedings of the ArXiv Preprint, 2016, arXiv:1609.02907. 
  11. J. Tang and K. Wang, "Personalized Top-N sequential recommendation via convolutional sequence embedding," in Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining (WSDM '18), pp.565-573, Feb. 5-9, New York, 2018. 
  12. F. Sun, J. Liu, J. Wu, C. Pei, X. Lin, W. Ou, and P. Jiang, "BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer," in Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM), pp. 1441-1450, Nov. 3-7, Beijing, China, 2019. 
  13. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "Bert: Pre-training of deep bidirectional transformers for language understanding," in Proceedings of the ArXiv Preprint, 2018, arXiv:1810.04805.