FEDGNNREC: A FEDERATED GRAPH NEURAL NETWORK FRAMEWORK FOR PRIVACY-PRESERVING RECOMMENDATIONS
DOI:
https://doi.org/10.70917/ijcisim-2026-3392Keywords:
Federated Learning, , Graph Neural Networks, Recommender Systems, Privacy-Preserving Machine Learning, User–Item Graphs, Decentralized Training, Federated Averaging, Deep Learning, Recommendation Accuracy, Non-IID DataAbstract
Recommender systems are common in today's online platforms to give personalised recommendations RS depending on the interaction of the users. Nevertheless, the conventional centralised recommendation methods demand gathering user information in central servers, which poses a serious privacy risk and a higher risk of information leakage. Concurrently, most of the traditional models do not reflect the structural relations that exist between the user and item interactions. In order to resolve these problems, this paper will suggest a FGNN framework, in which privacy-preserving recommendation is provided. The method proposed is a federated learning, which is merged with GNN to allow decentralised training whilst maintaining the relational structure of data in terms of interaction. All the clients build a local user-item graph and learn GNN-based embedding without distributing raw data. The aggregating server receives updates on the model by a federated averaging mechanism in order to construct a global model. The experimental results with Amazon review data indicate that the proposed federated GNN has a correlation of 0.9176, RMSE of 0.4021, and MAE of 0.2135, which is better than multiple centralised and base methods. Full privacy is also guaranteed by the model since the user data is not transferred to any other clients. These findings demonstrate the usefulness of federated graph-based learning in order to have secure and accurate recommendation systems.
Downloads
References
Wang, Y., Su, Z., Pan, Y., Luan, T. H., Li, R., & Yu, S. (2024). Social-Aware Clustered Federated Learning with Customized Privacy Preservation. https://doi.org/10.1109/TNET.2024.3379439
Neumann, D., Lutz, A., Müller, K., & Samek, W. (2025). A Privacy Preserving System for Movie Recommendations Using Federated Learning. ACM Transactions on Recommender Systems, 3(2), 1–51. https://doi.org/10.1145/3634686
Sun, H., Tu, Z., Sui, D., Zhang, B., & Xu, X. (2024). A Federated Social Recommendation Approach with Enhanced Hypergraph Neural Network. ACM Transactions on Intelligent Systems and Technology, 16(1). https://doi.org/10.1145/3665931
Ma, C., Ren, X., Xu, G., & He, B. (2023). FedGR: Federated Graph Neural Network for Recommendation Systems. Axioms, 12(2). https://doi.org/10.3390/axioms12020170
Wu, Y., Su, L., Wu, L., & Xiong, W. (2023). FedDeepFM: A Factorization Machine-Based Neural Network for Recommendation in Federated Learning. IEEE Access, 11, 74182–74190. https://doi.org/10.1109/ACCESS.2023.3295894
Malempati, K., Kotigari, P. R., Kandukuri, S. T., & Eirinaki, M. (2024). Federated Learning on Recommender Systems. Proceedings - 2024 IEEE International Conference on Big Data, BigData 2024, 7085–7094. https://doi.org/10.1109/BigData62323.2024.10825895
Qu, Z., Ding, J., Jhaveri, R. H., Djenouri, Y., Ning, X., & Tiwari, P. (2024). FedSarah: A Novel Low-Latency Federated Learning Algorithm for Consumer-Centric Personalized Recommendation Systems. IEEE Transactions on Consumer Electronics, 70(1), 2675–2686. https://doi.org/10.1109/TCE.2023.3342100
Xu, Z., Li, B., & Cao, W. (2025). Enhancing federated learning-based social recommendations with graph attention networks. Neurocomputing, 617, 129045.
Peng, Sony, Siet, S., Sadriddinov, I., Kim, D.-Y., Park, K., & Park, D.-S. (2025). Integration of Federated Learning and Graph Convolutional Networks for Movie Recommendation Systems. Computers, Materials & Continua, 83(2), 2041–2057. https://doi.org/10.32604/cmc.2025.061166
Ali, W., Zhou, X., & Shao, J. (2025). Privacy-preserved and Responsible Recommenders: From Conventional Defense to Federated Learning and Blockchain. ACM Computing Surveys, 57(5), 1–35. https://doi.org/10.1145/3708982
Huang, J., Tong, Z., & Feng, Z. (2022). Geographical POI recommendation for Internet of Things: A federated learning approach using matrix factorization. International Journal of Communication Systems, 38(17). https://doi.org/10.1002/dac.5161
Di, Y., Shi, H., Ma, R., Gao, H., Liu, Yuan, & Wang, W. (2025). FedRL: A Reinforcement Learning Federated Recommender System for Efficient Communication Using Reinforcement Selector and Hypernet Generator. ACM Transactions on Recommender Systems, 4(1), 1–31. https://doi.org/10.1145/3682076
Zeng, J., Huang, Z., Wu, Z. et al. FedGR: Cross-platform federated group recommendation system with hypergraph neural networks. J Intell Inf Syst 63, 227–257 (2025). https://doi.org/10.1007/s10844-024-00887-4
Yuan, W., Yang, C., Qu, L., Hung Nguyen, Q. V., Ye, G., & Yin, H. (2025). PTF-FSR: A Parameter Transmission-Free Federated Sequential Recommender System. ACM Transactions on Information Systems, 43(2), 1–24. https://doi.org/10.1145/3708344
He, Y., Wei, L., Chen, F., Zhang, Hanlin, Yu, J., & Wang, Haiyang. (2025). Fedai: Federated recommendation system with anonymized interactions. Expert Systems with Applications, 271, 126564. https://doi.org/10.1016/j.eswa.2025.126564
Di, Y., Shi, H., Wang, Q. et al. Federated cross-domain recommendation system based on bias eliminator and personalized extractor. Knowl Inf Syst 67, 2935–2965 (2025). https://doi.org/10.1007/s10115-024-02316-y
