Recommender Systems: Learning Collaborative Filtering Similarity Measures Using Siamese Networks

Jesús Bobadilla; Abraham Gutiérrez

doi:10.9781/ijimai.2025.03.006

Authors

Jesús Bobadilla Universidad Politécnica de Madrid
Abraham Gutiérrez Universidad Politécnica de Madrid

DOI:

https://doi.org/10.9781/ijimai.2025.03.006

Keywords:

Collaborative Filtering, Neural Networks, One-Hot Encoding, Recommender System, Siamese Networks, Similarity Measure

Supporting Agencies

This work was partially supported by Ministerio de Ciencia e Innovación of Spain under the project PID2019-106493RB-I00 (DLCEMG) and the Comunidad de Madrid under Convenio Plurianual with the Universidad Politécnica de Madrid in the actuation line of Programa de Excelencia para el Profesorado Universitario.

Abstract

Improving current similarity measures in the collaborative filtering Recommender Systems is relevant, since it contributes to different applications such as to get better big data representations of users and items, to implement dynamic browsers able to navigate through data, and to explain recommendation results. Currently, there are many statistically based similarity measures, some of them tailored to the extraordinarily sparse collaborative filtering scenario. Nevertheless, the hypothesis of the paper is that using neural networks, learnt similarity measures can be obtained that improve existing ones. To accomplish the task, the typical neural models cannot be used, and it is necessary to focus on the similarity learning area, in which the goal is to make the modellearn, which is a similarity function able to measure how similar two objects are. Siamese networks adequately implement the similarity learning concept, and we have adapted them to collaborative filtering particularities. The results in different scenarios show significant improvements compared to the state-of-the-art.

Downloads

Download data is not yet available.

References

Z. Shuai, Y. Lina, S., Aixin, T. Yi, “Deep Learning Based Recommender System: A Survey and New Perspectives,” ACM computing surveys, vol. 52, no. 1, pp. 1-38, 2019, doi: 10.1145/3285029.

J. Bobadilla, A. González-Prieto, F. Ortega, R. Lara Cabrera, “Deep learning feature selection to unhide demographic recommender systems factors,” Neural Computing & Applications, vol. 33, pp. 7291-7308, 2021, doi: 10.1007/s00521-020-05494-2.

R. Bawack, E. Bonhoure, “Influencer is the New Recommender: insights for Theorising Social Recommender Systems,” Information Systems Frontiers, vol. 25, pp. 183-197, 2023, doi: 10.1007/s10796-022-10262-9.

S. Raza, C. Ding, “Progress in context-aware recommender systems - An overview,” Computer Science Review, vol. 31, pp. 84-97, 2019, doi: 10.1016/j.cosrev.2019.01.001.

J. Bobadilla, A. González-Prieto, F. Ortega, R. Lara Cabrera, “Deep learning approach to obtain collaborative filtering neighborhoods,” Neural Computing & Applications, vol. 34, pp. 2939-2951, 2022, doi: 10.1007/s00521-021-06493-7.

X. Liao, X. Li, Q. Xu, H. Wu, Y. Wan, “Improving Ant Collaborative Filtering on Sparsity via Dimension Reduction,” Applied Sciences, vol. 10, no. 20, pp. 1-10, 2020, doi: 10.3390/app10207245.

T. Anwar, V. Uma, I. Hussain, M. Pantula, “Collaborative filtering and kNN based recommendation to overcome cold start and sparsity issues: A comparative analysis,” Multimedia Tools and Applications, vol. 81, pp. 35693-35711, 2022, doi: 10.1007/s11042-021-11883-z.

X. Hong-Jian, D. Xinyu, Z. Jianbing, H. Shujian, C. Jiajun, “Deep Matrix Factorization Models for Recommender Systems,” IJCAI’17: Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp. 3203-3209, 2017, doi: 10.5555/3172077.3172336.

H. Xiangnan, L. Lizi, Z. Hanwang, “Neural Collaborative Filtering,” WWW ‘17: Proceedings of the 26th International Conference on World Wide Web, pp. 173-182, 2017, doi: 10.1145/3038912.3052569.

M. Mendoza, N. Torres, “Evaluating content novelty in recommender systems,” Journal of Intelligent Information Systems, vol. 54, pp. 297-316, 2020, doi: 10.1007/s10844-019-00548-x.

M. Kunaver, T. Požrl, “Diversity in recommender systems - A survey,” Knowledge-Based Systems, vol. 123, pp. 154-162, 2017, doi: 10.1016/j.knosys.2017.02.009.

J. Bobadilla, A. Gutiérrez, S. Alonso, A. González-Prieto, “Neural collaborative filtering classification model to obtain prediction reliabilities,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 7, no. 4, pp. 18-26, 2022, doi: 10.9781/ijimai.2021.08.010.

A. Rago, O. Cocarascu, C. Bechlivanidis, D. Lagnado, F. Toni, “Argumentative explanations for interactive recommendations,” Artificial Intelligence, vol. 296, pp. 103506, 2021, doi: 10.1016/j.artint.2021.103506.

D. Medel, C.S. González-González, S.V. Aciar, “Social Relations and Methods in Recommender Systems: A Systematic Review,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 7, no. 4, pp. 7-17, 2022, doi: 10.9781/ijimai.2021.12.004.

A. Hernando, J. Bobadilla, F. Ortega, A. Gutiérrez, “Method to interactively visualize and navigate related information,” Expert Systems with Applications, vol. 111, pp. 61-75, 2018, doi: 10.1016/j.eswa.2018.01.034.

D. Kumar, S. Ray, “Approaches and algorithms to mitigate cold start problems in recommender systems: a systematic literature review,” Journal of Intelligent Information Systems, vol. 59, pp. 341-366, 2022, doi: 10.1007/s10844-022-00698-5.

H.J. Ahn, “A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem,” Information Sciences. vol. 178, no. 1, pp. 37-51, 2008, doi: 10.1016/j.ins.2007.07.024.

N. Serrano, A. Bellogín, “Siamese neural networks in recommendation,” Neural Computing & Applications, vol. 35, pp. 13941-13953, 2023, doi: 10.1007/s00521-023-08610-0.

A. Faroughi, P. Moradi, “MOOCs Recommender System with Siamese Neural Network,” 2022 9th International and the 15th National Conference on E-Learning and E-Teaching (ICeLeT), pp. 1-6, 2022, doi: 10.1109/ICeLeT55619.2022.9765439.

M. Jian, C. Zhang, M. Liu, X. Fu, S. Li, G. Shi, L. Wu, “Siamese Graph-Based Dynamic Matching for Collaborative Filtering,” Information Sciences, vol. 611, pp. 185-198, 2022, doi: 10.1016/j.ins.2022.08.062.

Q. Wang, R. Zhang, K. Ma, B. Chen, J. Chen, X. Shi, “Siamese Generative Adversarial Predicting Network for Extremely Sparse Data in in Recommendation System,” 2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), pp. 1236-1241, doi: 10.1109/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00170.

G. Gao, L. Liu, L. Wang, Y. Zhang, “Fashion clothes matching scheme based on siamese network and autoencoder,” Multimedia Systems, vol. 25, pp. 593-602, 2019, doi: 10.1007/s00530-019-00617-9.

M. Pulis, J. Bajada, “Siamese neural networks for content-based cold-start music recommendation,” RecSys ‘21: Proceedings of the 15th ACM Conference on Recommender Systems, pp. 719-723, 2021, doi: 10.1145/3460231.3478847.

F. Ortega, B. Zhu, J. Bobadilla, A. Hernando, “Cf4j: Collaborative filtering for java”, Knowledge-Based Systems, vol. 152, pp. 94–99, 2018, doi: 10.1016/j.knosys.2018.04.008.

J. Bobadilla, A. Gutiérrez, SiameseRS, GitHub repository, 2025. Accessed: Mar. 6, 2025 [Online]. Available: https://github.com/jesusbobadilla/SiameseRS.