بهبود عملکرد سیستم توصیه گر اجتماعی مبتنی بر شبکه کانولوشن گراف
طالب خفـائی
1
(
دانشکده فنی و مهندسی، دانشگاه ازاد اسلامی واحد بوشهر، بوشهر، ایران
)
محمد مهدی اسدی پور
2
(
دانشگاه آزاد اسلامی واحد بوشهر، بوشهر، ایران
)
کلید واژه: توصیه اجتماعی, گراف شبکه های کانولوشن, سیستم های توصیه گر, شبکه های اجتماعی,
چکیده مقاله :
سیستمهای توصیهگر الگوریتمهای پیچیدهای هستند که توسط کسبوکارها برای شخصیسازی و بهبود تجربیات کاربر استفاده میشوند. با تجزیه و تحلیل رفتار کاربر، اولویتها و دادههای تاریخی، سیستمهای توصیهگر میتوانند به طور موثر توصیههای شخصیسازی شده برای محصولات، خدمات یا محتوا را به کاربران ارائه دهند. از طریق استفاده از فناوریهای یادگیری ماشین و هوش مصنوعی، سیستمهای توصیهگر بهطور پیوسته یاد میگیرند و در طول زمان با ترجیحات کاربر سازگار میشوند. در این پژوهش، مدلی جدیدی ارائه شده است که با هدف بهبود دقت و کارایی سیستمهای توصیهگر توسعه یافته است. مدل پیشنهادی به صورت یکپارچه، شبکه تعاملات کاربر-آیتم، شبکه اجتماعی کاربران و شبکه تشابه مشارکتی آیتمها را در یک ساختار گرافی مدلسازی میکند. نتایج تجربی بهدستآمده از مجموعه داده واقعی میباشد که مدل پیشنهادی عملکرد بهتری نسبت به دو پژوهش NGCF و LightGCN را نشان میدهند. معیارهای NDCG و Recall به ترتیب بهبود 14% و 9% را نسبت به پژوهشهای بیان شده نشان دادهاند. این نتایج به وضوح نشان میدهد که ترکیب اطلاعات اجتماعی کاربران و روابط تشابه مشارکتی آیتمها میتواند بهطور قابلتوجهی عملکرد سیستمهای توصیهگر را ارتقاء دهد..
چکیده انگلیسی :
Recommender systems are complex algorithms used by businesses to personalize and improve user experiences. By analyzing user behavior, preferences, and historical data, recommender systems can effectively provide users with personalized recommendations for products, services, or content. Through the use of machine learning and artificial intelligence technologies, recommender systems continuously learn and adapt to user preferences over time. In this research, a new model has been presented, which was developed with the purpose of improving the accuracy and efficiency of recommender systems. The proposed model integrated models the user-item interaction network, the social network of users, and the cooperative similarity network of items in a graph structure. The experimental results obtained from real datasets show that the proposed model performs better than the two research methods, NGCF and LightGCN. The NDCG and Recall criteria showed a 14% and 9% improvement, respectively, compared to the previous research. These results clearly show that combining users' social information and collaborative similarity relationships of items can significantly improve the performance of recommender systems.
[1] Yin, C., Shi, L., Sun, R., & Wang, J. (2020). Improved collaborative filtering recommendation algorithm based on differential privacy protection. The Journal of Supercomputing, 76, 5161-5174.
[2] Wu, L., Sun, P., Fu, Y., Hong, R., Wang, X., & Wang, M. (2019, July). A neural influence diffusion model for social recommendation. In Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval (pp. 235-244).
[3] Wu, L., He, X., Wang, X., Zhang, K., & Wang, M. (2022). A survey on accuracy-oriented neural recommendation: From collaborative filtering to information-rich recommendation. IEEE Transactions on Knowledge and Data Engineering, 35(5), 4425-4445.
[4] Wang, X., Ma, W., Guo, L., Jiang, H., Liu, F., & Xu, C. (2022). Hgnn: Hyperedge-based graph neural network for mooc course recommendation. Information Processing & Management, 59(3), 102938.
[5] Wu, L., Li, J., Sun, P., Hong, R., Ge, Y., & Wang, M. (2020). Diffnet++: A neural influence and interest diffusion network for social recommendation. IEEE Transactions on Knowledge and Data Engineering, 34(10), 4753-4766.
[6] Fan, W., Ma, Y., Li, Q., He, Y., Zhao, E., Tang, J., & Yin, D. (2019, May). Graph neural networks for social recommendation. In The world wide web conference (pp. 417-426).
[7] Li, Y., Zhan, Z., Li, H., & Liu, C. (2022). Interest-aware influence diffusion model for social recommendation. Journal of Intelligent Information Systems, 1-15.
[8] Zhou, Y., Liu, L., Lee, K., Palanisamy, B., & Zhang, Q. (2020). Improving collaborative filtering with social influence over heterogeneous information networks. ACM Transactions on Internet Technology (TOIT), 20(4), 1-29.
[9] Wu, L., Sun, P., Hong, R., Ge, Y., & Wang, M. (2018). Collaborative neural social recommendation. IEEE transactions on systems, man, and cybernetics: systems, 51(1), 464-476.
[10] Sun, P., Wu, L., & Wang, M. (2018, June). Attentive recurrent social recommendation. In The 41st international ACM SIGIR conference on research & development in information retrieval (pp. 185-194).
[11] Cao, Q., Yin, Q., Song, Y., Wang, Z., Chen, Y., Da Xu, R. Y., & Yang, X. (2023, June). RTANet: Recommendation Target-Aware Network Embedding. In Proceedings of the International AAAI Conference on Web and Social Media (Vol. 17, pp. 84-94).
[12] Hossain, I., Puppala, S., Alam, M. J., & Talukder, S. (2024). SocialRec: User Activity Based Post Weighted Dynamic Personalized Post Recommendation System in Social Media. arXiv preprint arXiv:2407.09747.
[13] Rajput, S., Mehta, N., Singh, A., Hulikal Keshavan, R., Vu, T., Heldt, L., ... & Sathiamoorthy, M. (2024). Recommender systems with generative retrieval. Advances in Neural Information Processing Systems, 36.
[14] Lakshmi, T. J., & Bhavani, S. D. (2024). Link prediction approach to recommender systems. Computing, 106(7), 2157-2183.
[15] Ge, Y., Huang, C., Liu, Y., Zhang, S., & Kong, W. (2024). Unsupervised social network embedding via adaptive specific mappings. Frontiers of Computer Science, 18(3), 183310.
[16] He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., & Wang, M. (2021, July). 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 (pp. 639-648).
[17] Dos Santos, L., Piwowarski, B., & Gallinari, P. (2017, August). Gaussian embeddings for collaborative filtering. In Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval (pp. 1065-1068).
[18] Tang, J., Hu, X., & Liu, H. (2013). Social recommendation: a review. Social Network Analysis and Mining, 3, 1113-1133.
[19] Bennett, J., & Lanning, S. (2007, August). The netflix prize. In Proceedings of KDD cup and workshop (Vol. 2007, p. 35).
[20] Koren, Y., & Bell, R. (2015). Advances in Collaborative Filtering, Recommender Systems Handbook, Editör: Ricci, F., Rokach, L., Shapira, B.
[21] Bell, R. M., & Koren, Y. (2007, October). Scalable collaborative filtering with jointly derived neighborhood interpolation weights. In Seventh IEEE international conference on data mining (ICDM 2007) (pp. 43-52). IEEE.
[22] Ahmad, H. K., Qi, C., Wu, Z., & Muhammad, B. A. (2023). ABiNE-CRS: course recommender system in online education using attributed bipartite network embedding. Applied Intelligence, 53(4), 4665-4684.
[23] Chang, J., Gao, C., Zheng, Y., Hui, Y., Niu, Y., Song, Y., ... & Li, Y. (2021, July). Sequential recommendation with graph neural networks. In Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval (pp. 378-387).
[24] Chen, C., Guo, J., & Song, B. (2021, July). Dual attention transfer in session-based recommendation with multi-dimensional integration. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 869-878).
