Federated Learning for E-Commerce Recommendation Systems: A Survey on Privacy-Preserving Personalization

Nier Mou

doi:10.54097/t268s726

Authors

Nier Mou

DOI:

https://doi.org/10.54097/t268s726

Keywords:

Federated learning; data privacy; recommendation system; E-Commerce.

Abstract

In the information age, while e-commerce recommendation systems enhance user experience, they also face a significant risk of user privacy leakage. Traditional privacy protection technologies (such as K-anonymity and differential privacy) often come at the expense of data utility and recommendation accuracy. Federated learning, as an emerging distributed machine learning paradigm, offers a promising solution to the tension between privacy and personalization through its core principle of ‘data remains local, models move”. This paper reviews the latest progress in federated learning for e-commerce recommendation, focusing on analyzing federated recommendation architectures based on deep neural networks (such as FedPrivRec) and natural language processing, as well as their applications in cross-merchant collaboration, privacy protection, and other areas. Meanwhile, this paper examines the primary challenges currently faced by federated recommendation systems, including privacy attacks such as member inference, data heterogeneity, as well as communication and computational efficiency bottlenecks and cost pressures. Finally, future research directions, such as the optimization of communication and hardware computing power, were prospected, aiming to serve as a reference for building a privacy-secure, efficient, and sustainable e-commerce recommendation system service.

References

[1]Loukides G, Shao J. Capturing data usefulness and privacy protection in K-anonymisation. In: Proceedings of the 2007 ACM Symposium on Applied Computing; 2007 Mar 11–14; Seoul, Korea. New York: ACM; 2007. p. 370–4.

[2]Duncan G, Stokes L. Data masking for disclosure limitation. Wiley Interdisciplinary Reviews: Computational Statistics, 2009, 1(1): 83-92.

[3]Zhao J, Chen Y, Zhang W. Differential privacy preservation in deep learning: Challenges, opportunities and solutions. IEEE Access, 2019, 7: 48901-48911.

[4]Li J T, Cui T X, Yang K W, et al. Demand forecasting of E-commerce enterprises based on horizontal federated learning from the perspective of sustainable development. Sustainability, 2021, 13(23): 13050.

[5]Mothukuri V, Parizi R M, Pouriyeh S, et al. A survey on security and privacy of federated learning. Future Generation Computer Systems, 2021, 115: 619-640.

[6]Yang Q, Liu Y, Chen T, et al. Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 2019, 10(2): 1-19.

[7]Ji S, Liang Y, Xiao X, et al. An attitude-adaptation negotiation strategy in electronic market environments. In Proceedings of the Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, Qingdao, China, 2007, 3: 125-130.

[8]Wang Q Y, Yin H Z, Chen T, et al. Fast-adapting and privacy-preserving federated recommender system. The VLDB Journal, 2022, 31(5): 877-896.

[9]Lee K J, Jeong B, Kim S, et al. General commerce intelligence: Glocally federated NLP-based engine for privacy-preserving and sustainable personalized services of multi-merchants. In Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, Canada, 2024, 38(21): 22752-22760.

[10]Melis L, Song C, De Cristofaro E, et al. Exploiting unintended feature leakage in collaborative learning. In Proceedings of the IEEE Symposium on Security and Privacy, San Francisco, CA, USA, 2019: 691-706.

[11]Pei J, Liu W, Li J, et al. A review of federated learning methods in heterogeneous scenarios. IEEE Transactions on Consumer Electronics, 2024, 70(3): 5983-5999.

[12]Yu X, Liu Z, Sun Y, et al. Clustered federated learning for heterogeneous data (student abstract). In Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA, 2023, 37: 16378-16379.

[13]Panchal K, Choudhary S, Parikh N, et al. Flow: per-instance personalized federated learning. Advances in Neural Information Processing Systems, 2023, 36: 18712-18755.

[14]Bharati S, Mondal M R H, Podder P, et al. Federated learning: Applications, challenges and future directions. International Journal of Hybrid Intelligent Systems, 2022, 18(1-2): 19-35.