ANALYZING FUSION MECHANISMS IN MULTI-BEHAVIOR RECOMMENDATION SYSTEMS
Abstract
Analysis of fusion mechanisms in multi-behavior recommendation on the Taobao dataset for predicting purchase behavior under sparse and imbalanced conditions. Four fusion strategies are examined: early fusion (BPR-MF with Weighted Sum), late fusion (NeuMF), intermediate fusion (MBGCN), and model-level fusion (PLE). Experimental results show that PLE achieved the highest Recall and Precision, while MBGCN achieved the highest NDCG, reflecting its ability to improve ranking quality at the top positions. Overall, simultaneously leveraging multiple auxiliary user behaviors such as viewing, liking, and adding to cart enhances the effectiveness of predicting purchase behavior in a sparse and unbalanced data environment.
Tài liệu tham khảo
[1] C. Gao, S. Li, W. Lei, B. Li, P. Jiang, M. de Rijke and X. He, “Multi-behavior Recommendation: A Survey,” IEEE Transactions on Knowledge and Data Engineering, pp. 1-18, 2023.
[2] A. Cloud, “User Behavior Data from Taobao for Recommendation,” 2017.
[3] 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, Xi'an, 2020.
[4] S. Dhelim, N. Aung, H. Wang, H. Ning, K. Xu and Q. Zhang, “A Survey on Multi-Behavior Recommendation,” IEEE Access, vol. 10, pp. 90333-90353, 2022.
[5] X. He, L. Liao, H. Zhang, L. Nie, X. Hu and T.-S. Chua, “Neural Collaborative Filtering,” in Proceedings of the 26th International Conference on World Wide Web, Perth, 2017.
[6] H. Zhu, X. Li, P. Zhang, G. Li, J. He, C. Li and J. Xiao, “Learning Tree-based Deep Model for Recommender Systems,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, 2018.
[7] H. Tang, J. Liu, M. Zhao and X. Gong, “Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations,” in Proceedings of the 14th ACM Conference on Recommender Systems (RecSys '20), Rio de Janeiro, 2020.
[8] S. Wu, F. Sun, W. Zhang, X. Xie and B. Cui, “Graph Neural Networks in Recommender Systems: A Survey,” ACM Computing Surveys, vol. 55, no. 5, pp. 1-37, 2022.
[9] F. Ricci, L. Rokach and B. Shapira, Recommender Systems Handbook, 3rd ed., New York: Springer, 2022.
[10] Y. Koren, R. Bell and C. Volinsky, “Matrix Factorization Techniques for Recommender Systems,” IEEE Computer, vol. 42, no. 8, pp. 42-49, 2009.
[11] B. Jin, C. Gao, X. He, D. Jin and Y. Li, “Multi-behavior Recommendation with Graph Convolutional Networks,” in Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Xi'an, 2020.
[12] J. Yu, H. Yin, X. Xia, Z. Zhu, L. Cui and Q. V. H. Nguyen, “Self-Supervised Learning for Recommender Systems: A Survey,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 12, pp. 1-20, 2023.
[13] S. Rendle, C. Freudenthaler, Z. Gantner and L. Schmidt-Thieme, “BPR: Bayesian Personalized Ranking from Implicit Feedback,” in Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence (UAI '09), Montreal, 2009.
[14] J. Chen, H. Dong, X. Wang, F. Feng, M. Wang and X. He, “Bias and Debias in Recommender System: A Survey and Future Directions,” ACM Transactions on Information Systems, vol. 41, no. 3, pp. 1-39, 2023.
[15] J. Lin, X. Dai, Y. Xi, W. Liu, B. Chen and X. Li, “Recommender Systems in the Era of Large Language Models (LLMs),” IEEE Transactions on Knowledge and Data Engineering, vol. 36, no. 7, pp. 1-22, 2024.
[16] K. Wang, Y. Wang, Y. Xi, W. X. Zhao and J.-R. Wen, “A Comprehensive Survey on Loss Functions in Recommender Systems,” arXiv preprint arXiv:2312.01375 (hoặc nhập ACM Computing Surveys), pp. 1-35, 2024.
[17] S. Dhelim, N. Aung, H. Wang and H. Ning, “A Survey on Multi-Behavior Recommendation,” IEEE Access (Hoặc dùng bài Survey về Deep Learning tổng quát), 2022.
[18] E. Yang, X. Xin, N. Liu, G. Guo and H. Xiong, “Multi-Task Learning for Recommender Systems: A Survey,” arXiv preprint arXiv:2305.15582 (hoặc IEEE Transactions), pp. 1-20, 2023.
[19] J. Ma, Z. Zhao, X. Yi, J. Chen, L. Hong and E. H. Chi, “Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, 2018.
[20] S. Dhelim, N. Aung, H. Wang, H. Ning, K. Xu and Q. Zhang, “A Survey on Multi-Behavior Recommendation,” IEEE Access, vol. 10, pp. 90333-90353, 2022