Neural Collaborative Filtering Classification Model to Obtain Prediction Reliabilities

  1. Jesús Bobadilla 1
  2. Abraham Gutiérrez 1
  3. Santiago Alonso 1
  4. Ángel González Prieto 1
  1. 1 Universidad Politécnica de Madrid
    info

    Universidad Politécnica de Madrid

    Madrid, España

    ROR https://ror.org/03n6nwv02

Revista:
IJIMAI

ISSN: 1989-1660

Ano de publicación: 2022

Volume: 7

Número: 4

Páxinas: 18-26

Tipo: Artigo

DOI: 10.9781/IJIMAI.2021.08.010 DIALNET GOOGLE SCHOLAR lock_openDialnet editor

Outras publicacións en: IJIMAI

Resumo

Neural collaborative filtering is the state of art field in the recommender systems area; it provides some models that obtain accurate predictions and recommendations. These models are regression-based, and they just return rating predictions. This paper proposes the use of a classification-based approach, returning both rating predictions and their reliabilities. The extra information (prediction reliabilities) can be used in a variety of relevant collaborative filtering areas such as detection of shilling attacks, recommendations explanation or navigational tools to show users and items dependences. Additionally, recommendation reliabilities can be gracefully provided to users: “probably you will like this film”, “almost certainly you will like this song”, etc. This paper provides the proposed neural architecture; it also tests that the quality of its recommendation results is as good as the state of art baselines. Remarkably, individual rating predictions are improved by using the proposed architecture compared to baselines. Experiments have been performed making use of four popular public datasets, showing generalizable quality results. Overall, the proposed architecture improves individual rating predictions quality, maintains recommendation results and opens the doors to a set of relevant collaborative filtering fields.

Referencias bibliográficas

  • K. Madadipouya, S. Chelliah, “A Literature Review on Recommender Systems Algorithms, Techniques and Evaluations”, Brain: Broad Research in Artificial Intelligence and Neuroscience, vol. 8, no. 2, 2017, pp. 109-124.
  • S.S. Sohail, J. Siddiqui, R. Ali, “Classifications of Recommender Systems: A review”, Journal of Engineering Science and Technology Review, vol. 10, no. 4, 2017, pp. 132-153.
  • H. Zamani, A. Shakery, “A language model-based framework for multipublisher content-based recommender systems”, Information Retrieval Journal, vol. 21, no. 5, 2018, pp. 369-409.
  • M.Y.H. Al-Shamri, “User profiling approaches for demographic recommender systems”, Knowledge-Based Systems, vol. 100, 2016, pp. 175-187.
  • N.M. Villegas, C. Sánchez, J. Díaz-Cely, G. Tamura, “Characterizing context-aware recommender systems: A systematic literature review”, Knowledge-Based Systems, vol. 140, 2018, pp. 173-200.
  • A. Rezvanian, B. Moradabadi, M. Ghavipour, M.M. Daliri Khomami, M.R. Meybodi, “Social recommender systems”, Studies in Computational Intelligence, vol. 820, 2019, pp. 281-313.
  • A. Hernando, J. Bobadilla, F. Ortega, A. Gutiérrez, “A probabilistic model for recommending to new cold-start non-registered users”, Information Sciences, vol. 376, 2017, pp. 216-232.
  • J. Bobadilla, A. Gutiérrez, S. Alonso, R. Hurtado, “A Collaborative Filtering Probabilistic Approach for Recommendation to Large Homogeneous and Automatically Detected Groups”, International Journal of Interactive Multimedia and Artificial Intelligence, 2020, doi: 10.9781/ijimai.2020.03.002.
  • V. Yu. Ignat’ev, D. V. Lemtyuzhnikova, D. I. Rul’, I. L. Ryabov, “Constructing a Hybrid Recommender System”, Journal of Computer and Systems Sciences International, vol. 57, no. 6, 2018, pp. 921-926.
  • H. Li, Y. Liu, Y. Qian, N. Mamoulis, W. Tu, Wenting ; D. Cheung, “HHMF: hidden hierarchical matrix factorization for recommender systems”, Data Mining and Knowledge Discovery, vol. 33, no. 6, 2019, pp. 1548-1582.
  • H. Xiangnan, L. Lizi, Z. Hanwang, “Neural Collaborative Filtering”, in International World Wide Web Conference Committee (IW3C2), Perth, Australia, 2017, doi: 10.1145/3038912.3052569
  • D. Bokde, S. Girase, D. Mukhopadhyay, “Matrix Factorization Model in Collaborative Filtering Algorithms: A Survey”, Procedia Computer Science, vol. 49, 2015, pp. 136-146, doi: 10.1016/j.procs.2015.04.237.
  • S. Rendle, W. Krichene, L. Zhang, J.R. Anderson, “Neural Collaborative Filtering vs. Matrix Factorization”, in RecSys ‘20: Fourteenth ACM Conference on Recommender Systems, Brasil, 2020, pp. 240–248, doi: 10.1145/3383313.3412488.
  • H.J. Xue, Xi. Dai, J. Zhang, S. Huang, J. Chen, “Deep Matrix Factorization Models for Recommender Systems”, in Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne, Australia, 2017, pp. 3203-3209, doi: 10.24963/ijcai.2017/447
  • Y. Liu, S.L. Wang, J.F. Zhang, W. Zhang, W. Li, “A neural collaborative filtering method for identifying miRNA-disease associations”, Neurocomputing, vol. 422, 2021, pp. 176-185.
  • L. Corinzia, F. Laumer, A. Candreva, M. Taramasso, F. Maisano, J.M. Buhmann, “Neural collaborative filtering for unsupervised mitral valve segmentation in echocardiography”, Artificial intelligence in medicine, vol. 110, 2020, pp. 101975-101975.
  • H. Gao, Y. Xu, Y. Yin, W. Zhang, R. Li, X. Wang, “Context-Aware QoS Prediction with Neural Collaborative Filtering for Internet-of-Things Services”, IEEE internet of things journal, vol. 7, no. 5, 2020, pp. 4532-4542, doi: 10.110’9/JIOT.2019.2956827.
  • J. Bobadilla, R. Lara-Cabrera, A. González-Prieto, F. Ortega, “DeepFair: Deep Learning for Improving Fairness in Recommender Systems”, International Journal Of Interactive Multimedia And Artificial Intelligence, 2020, doi: 10.9781/ijimai.2020.11.001.
  • F. Ullah, B. Zhang, R.U. Khan, T.S. Chung, M. Attique, K. Khan, S. Khediri, S. Jan, “Deep Edu: A Deep Neural Collaborative Filtering for Educational Services Recommendation”, IEEE access, vol. 8, 2020, pp. 110915-110928.
  • Y. Guo, Z. Yan, “Recommended System: Attentive Neural Collaborative Filtering”, IEEE access, vol. 8, 2020, pp. 125953-125960.
  • W. Chen, F. Cai, H. Chen, M. Rijke, “Joint Neural Collaborative Filtering for Recommender Systems”, ACM transactions on information systems, vol. 37, no. 4, 2019, pp. 1-30.
  • S. Yu, M. Yang, Min, Q. Qu, Y. Shen, “Contextual-boosted deep neural collaborative filtering model for interpretable recommendation”, Expert systems with applications, vol. 136, 2019, pp. 365-375.
  • L. Sang, M. Xu, S. Qian, X. Wu, “Knowledge graph enhanced neural collaborative recommendation”, Expert systems with applications, vol. 164, 2021, pp. 113992, doi: 10.1016/j.eswa.2020.113992.
  • C.Yang, L. Miao, B. Jiang, D. Li, D. Cao, “Gated and attentive neural collaborative filtering for user generated list recommendation”, Knowledge-based systems, vol. 187, 2020, pp. 104839.
  • T. Huang, D. Zhang, L. Bi, “Neural embedding collaborative filtering for recommender systems”, Neural computing & applications, vol. 32, no. 22, 2020, pp. 17043-17057.
  • M. Si, Q. Li, “Shilling attacks against collaborative recommender systems: a review”, The Artificial intelligence review, vol. 53, no. 1, 2018, pp. 291- 319.
  • F. Zhang, Z. Ling, S. Wang, “Unsupervised approach for detecting shilling attacks in collaborative recommender systems based on user rating behaviours”, IET information security, vol. 13, no. 3, 2019, pp. 174-187.
  • S. Alonso, J. Bobadilla, F. Ortega, R. Moya, “Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems”, IEEE access, vol. 7, 2019, pp. 41782-41798.
  • A. Hernando, J. Bobadilla, F. Ortega, A. Gutiérrez, “Method to interactively visualize and navigate related information”, Expert Systems with Applications, vol. 111, 2018, pp. 61-75.
  • A. Hernando, R. Moya, F. Ortega, J. Bobadilla, “Hierarchical graph maps for visualization of collaborative recommender systems”, Journal of Information Science, vol. 40, no. 1, 2014, pp. 97-106.
  • B. Zhu, F. Ortega, J. Bobadilla, A. Gutiérrez, “Assigning reliability values to recommendations using matrix factorization”, Journal of computational science, vol. 26, 2018, pp. 165-177.
  • S. Ahmadian, P. Moradi, F. Akhlaghian, Fardin, “An improved model of trust-aware recommender systems using reliability measurements”, in 6th Conference on Information and Knowledge Technology (IKT), Shahrud, Iran, 2014, pp. 98-103.
  • A. Hernando, J. Bobadilla, F. Ortega, J. Tejedor, “Incorporating reliability measurements into the predictions of a recommender system”, Information Sciences, vol. 218, 2013, pp. 1-16.
  • F. Ortega, R. Lara-Cabrera, A. González-Prieto, J. Bobadilla, “Providing reliability in recommender systems through Bernoulli Matrix Factorization”, Information sciences, vol. 553, 2021, pp. 110-128.
  • J. Bobadilla, A. Gutiérrez, F. Ortega, B. Zhu, “Reliability quality measures for recommender systems”, Information Sciences, Vol. 442-443, 2018, pp. 145-157
  • J. Bobadilla, F. Ortega, A. Gutierrez, S. Alonso, “Classification-based Deep Neural Network Architecture for Collaborative Filtering Recommender Systems”, International Journal of Interactive Multimedia and Artificial Intelligence, vol. 6, no. 1, 2020, pp. 68-77.
  • J. Bobadilla, S. Alonso, A. Hernando, “Deep learning architecture for collaborative filtering recommender systems”, Applied Sciences, vol. 10, no. 7, 2020, pp. 2441.
  • F.M. Harper, J.A. Konstan, “The movielens datasets: History and context”, International Journal of Interactive Multimedia and Artificial Intelligence, Vol. 7, Nº4 - 26 - ACM Transactions on Interactive Intelligent Systems, vol. 5, no. 4, 2015, pp. 1–19.
  • https://www.kaggle.com/azathoth42/myanimelist
  • F. Ortega, B. Zhu, J. Bobadilla, A. Hernando, “CF4J: Collaborative filtering for Java”, Knowledge-Based Systems, vol. 152, 2018, pp. 94–99.
Fonte de datos: Dialnet