Smart Media Journal (스마트미디어저널)

THE KOREAN INSTITUTE OF SMART MEDIA (한국스마트미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Extended Knowledge Graph using Relation Modeling between Heterogeneous Data for Personalized Recommender Systems

이종 데이터 간 관계 모델링을 통한 개인화 추천 시스템의 지식 그래프 확장 기법

  • 이승주 (인하대학교 전기컴퓨터공학과 ) ;
  • 안석호 (인하대학교 전기컴퓨터공학과 ) ;
  • 이의종 (충북대학교 소프트웨어학부) ;
  • 서영덕 (인하대학교 컴퓨터공학과 )
  • Received : 2023.03.09
  • Accepted : 2023.03.20
  • Published : 2023.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Many researchers have investigated ways to enhance recommender systems by integrating heterogeneous data to address the data sparsity problem. However, only a few studies have successfully integrated heterogeneous data using knowledge graph. Additionally, most of the knowledge graphs built in these studies only incorporate explicit relationships between entities and lack additional information. Therefore, we propose a method for expanding knowledge graphs by using deep learning to model latent relationships between heterogeneous data from multiple knowledge bases. Our extended knowledge graph enhances the quality of entity features and ultimately increases the accuracy of predicted user preferences. Experiments using real music data demonstrate that the expanded knowledge graph leads to an increase in recommendation accuracy when compared to the original knowledge graph.

많은 추천 시스템 연구에서는 다양한 이종 데이터를 상호 호환적으로 통합하여 추천 시스템의 고질적인 데이터 부족 문제를 해결하고자 한다. 하지만, 지식 그래프를 활용하여 이종 데이터의 통합을 달성한 추천 시스템 연구는 거의 없으며, 대부분 연구에서는 기구축된 지식 그래프 상의 개체 간 연결이 명시적 관계로만 구성되어있다는 한계가 존재한다. 본 논문에서는 이종 데이터의 통합을 위해 다중 지식 베이스로부터 추출한 데이터 간 관계 모델링을 수행하고, 이를 통해 지식 그래프를 확장하는 방법을 제안한다. 또한, 딥러닝 기반의 잠재적 관계 모델링을 통해 지식 그래프 상 개체 간 관계 정보의 신뢰성을 높이고자 한다. 본 논문에서 제안하는 확장된 지식 그래프를 사용하면 개체의 특성 벡터 품질이 개선되고, 최종적으로 예측된 사용자 선호도의 정확성을 높일 수 있다. 또한, 실험을 통해 확장된 지식 그래프 기반 추천 정확도가 기존 지식 그래프 기반 추천 정확도에 비해 향상되었음을 확인하였다.

Keywords

Acknowledgement

본 연구는 2022년도 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원(NRF-2022R1C1C1012408, 우수신진연구)과 정보통신기획평가원의 지원(No.2022-0-00448, 사람중심인공지능핵심원천기술개발, No.RS-2022-00155915, 인공지능융합혁신인재양성(인하대학교))을 받아 수행한 연구임.

References

  1. 김형숙, 이종혁, 이현동, "인공지능 기반 개인맞춤형 의류 추천 서비스 개발," 스마트미디어저널제10권, 제1호, 116-123쪽, 2021년 03월 
  2. Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu and Tat-Seng Chua, "Kgat: Knowledge graph attention network for recommendation," Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining(KDD '19), pp. 950-958, NewYork, NY, US, 2019. 
  3. Rui Sun, Xuezhi Cao, Yan Zhao, Junchen Wan, Kun Zhou, Fuzheng Zhang, Zhongyuan Wang and Kai Zheng, "Multi-modal knowledge graphs for recommender systems," Proceedings of the 29th ACM international conference on information & knowledge management(CIKM'20), pp. 1405-1414, New York, NY, US, 2020. 
  4. Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu and Tat-Seng Chua, "Neural collaborative filtering," Proceedings of the 26th international conference on world wide web, pp. 173-182, Republic and Canton of Geneva, Switzerland, 2017. 
  5. Xiting Wang, Kunpeng Liu, Dongjie Wang, Le Wu, Yanjie Fu and Xing Xie, "Multi-level recommendation reasoning over knowledge graphs with reinforcement learning," Proceedings of the ACM Web Conference 2022, pp. 2098-2108, New York, NY, US, 2022. 
  6. Sabino Metta, Paolo Casagranda, Alberto Messina, Maurizio Montagnuolo and Francesco Russo, "Leveraging MPEG-21 user description for interoperable recommender systems," Proceedings of the 31st Annual ACM Symposium on Applied Computing, pp. 1072-1074, New York, NY, US, 2016. 
  7. Mehrbakhsh Nilashi, Othman Ibrahim and Karamollah Bagherifard, "A recommender system based on collaborative filtering using ontology and dimensionality reduction techniques," Expert Systems with Applications, Vol. 92, pp. 507-520, Feb. 2018.  https://doi.org/10.1016/j.eswa.2017.09.058
  8. Stuart E Middleton, David C De Roure and Nigel R Shadbolt, "Capturing knowledge of user preferences: ontologies in recommender systems," Proceedings of the 1st international conference on Knowledge capture, pp. 100-107, New York, NY, US, 2001. 
  9. Xiang Wang, Dingxian Wang, Canran Xu, Xiangnan He, Yixin Cao and Tat-Seng Chua, "Explainable reasoning over knowledge graphs for recommendation," Proceedings of the AAAI conference on artificial intelligence, Vol. 33, pp. 5329-5336, Honolulu, Hawaii, USA, 2019. 
  10. A. Kim, S. Lee and K. Lee, "Ontology Construction for Interoperability and Scalability of Human-Object Interaction Datasets," Journal of KIISE, Vol.48, No.8, pp. 947-958, Aug. 2021.  https://doi.org/10.5626/JOK.2021.48.8.947
  11. C. Chung and J. J. Whang, "Knowledge Graph Embedding via Metagraph Learning," Proc. of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2212-2216, New York, NY, US, Jul. 2021. 
  12. S. Choi and S. Park, "A Knowledge Graph Embedding-based Ensemble Model for Link Prediction," Journal of KIISE, Vol.47, No.5, pp. 473-478, May 2020.  https://doi.org/10.5626/JOK.2020.47.5.473
  13. J. Roh, W. Shin, H.-K. Park and Y.-T. Park, "A Knowledge Completion Approach using Rule Generation based on Neuro-Symbolic Method," Journal of KIISE, Vol.48, No.4, pp. 425-433, Apr. 2021.  https://doi.org/10.5626/JOK.2021.48.4.425
  14. S. Kong, C. Chung, S. Ju and J. Whang, "Knowledge Graph Embedding with Entity Type Constraints," Journal of KIISE, Vol.49, No.9, pp. 773-779, Sep. 2022.  https://doi.org/10.5626/JOK.2022.49.9.773
  15. Bahram Amini, Roliana Ibrahim, Mohd Shahizan Othman and Mohammad Ali Nematbakhsh, "A reference ontology for profiling scholar's background knowledge in recommender systems," Expert Systems with Applications, Vol. 42, Issue 2, pp. 913-928, 2015.  https://doi.org/10.1016/j.eswa.2014.08.031
  16. Fabiana Freire de Araujo, Fernanda Ligia R Lopes and Bernadette Farias Loscio, "MeMO: A clustering-based approach for merging multiple ontologies," 2010 Workshops on database and expert systems applications, pp. 176-180, Bilbao, Spain, 2010. 
  17. Olawande Daramola, Mathew Adigun and Charles Ayo, "Building an ontology-based framework for tourism recommendation services," Information and Communication Technologies in Tourism, pp. 135-147, Amsterdam, Netherlands, 2009. 
  18. Hongwei Wang, Miao Zhao, Xing Xie, Wenjie Li and Minyi Guo, "Knowledge graph convolutional networks for recommender systems," The world wide web conference, pp. 3307-3313, New York, NY, US, 2019. 
  19. Weizhi Ma, Min Zhang, Yue Cao, Woojeong Jin, Chenyang Wang, Yiqun Liu, Shaoping Ma and Xiang Ren, "Jointly learning explainable rules for recommendation with knowledge graph," The world wide web conference, pp. 1210-1221, New York, NY, US, 2019. 
  20. Xiou Ge, Yun-Cheng Wang, Bin Wang and C.C. Jay Kuo, "CORE: A knowledge graph entity type prediction method via complex space regression and embedding," Pattern Recognition Letters, Vol. 157, pp. 97 103, May 2022. 
  21. R. Xie, Z. Liu and M. Sun, "Representation Learning of Knowledge Graphs with Hierarchical Types," Proc. of the 25th International Joint Con-ference on Artificial Intelligence, pp. 2965-2971, New York, NY, US, Jul. 2016. 
  22. Zhu Sun, Jie Yang, Jie Zhang, Alessandro Bozzon, Long-Kai Huang and Chi Xu, "Recurrent Knowledge Graph Embedding for Effective Recommendation," Proceedings of the 12th ACM Conference on Recommender Systems (RecSys '18), pp. 297-305, New York, NY, USA, 2018. 
  23. Thierry Bertin-Mahieux, Daniel PW Ellis, Brian Whitman and Paul Lamere, "The million song dataset," Proceedings of the 12th International Society for Music Information Retrieval Conference(ISMIR 2011), pp. 591-596, Miami, Florida, USA, 2011. 
  24. Wang, H., Zhang, F., Wang, J., Zhao, M., Li, W., Xie, X. and Guo, M, "Ripplenet: Propagating user preferences on the knowledge graph for recommender systems," Proceedings of the 27th ACM international conference on information and knowledge management, pp. 417-426, NewYork, NY, USA, Oct. 2018. 
  25. 홍택은, 유경호, 김판구, "전력 비즈니스 플랫폼기반의 전력 도메인 온톨로지 구축 및 추론 방법," 스마트미디어저널, 제9권, 제2호, 51-62쪽, 2020년06월 
  26. 이희준, 이원석, 최인혁, 이충권, "딥러닝을 이용한 시퀀스 기반의 여행경로 추천시스템-제주도사례-," 스마트미디어저널, 제9권, 제1호, 45-50쪽, 2020년 03월