A Comprehensive Survey on Privacy-Preserving Techniques in Federated Recommendation Systems
Source abstract
Abstract
Big data is a rapidly growing field, and new developments are constantly emerging to address various challenges. One such development is the use of federated learning for recommendation systems (FRSs). An FRS provides a way to protect user privacy by training recommendation models using intermediate parameters instead of real user data. This approach allows for cooperation between data platforms while still complying with privacy regulations. In this paper, we explored the current state of research on FRSs, highlighting existing research issues and possible solutions. Specifically, we looked at how FRSs can be used to protect user privacy while still allowing organizations to benefit from the data they share. Additionally, we examined potential applications of FRSs in the context of big data, exploring how these systems can be used to facilitate secure data sharing and collaboration. Finally, we discuss the challenges associated with developing and deploying FRSs in the real world and how these challenges can be addressed.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data · Recommender Systems and Techniques · Cryptography and Data Security
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Graduate School of Information Science and Technology, Department of Creative Informatics, The University of Tokyo, Tokyo 113-8654, Japan
Funding
National Institute of Information and Communications Technology (NICT), Japan
References (100+)
Show source-provided references
1. Fayyaz, Z., Ebrahimian, M., Nawara, D., Ibrahim, A., and Kashef, R. (2020). Recommendation systems: Algorithms, challenges, metrics, and business opportunities. Appl. Sci., 10.10.3390/app10217748 ↗
2. Naumov, M., Mudigere, D., Shi, H.J.M., Huang, J., Sundaraman, N., Park, J., Wang, X., Gupta, U., Wu, C.J., and Azzolini, A.G. (2019). Deep learning recommendation model for personalization and recommendation systems. arXiv.
3. Ko, H., Lee, S., Park, Y., and Choi, A. (2022). A survey of recommendation systems: Recommendation models, techniques, and application fields. Electronics, 11.10.3390/electronics11010141 ↗
4. Blockchain-based recommender systems: Applications, challenges and future opportunities10.1016/j.cosrev.2021.100439 ↗
5. Deldjoo, Y., Jannach, D., Bellogin, A., Difonzo, A., and Zanzonelli, D. (2022). A survey of research on fair recommender systems. arXiv.
6. Huang, J., Tong, Z., and Feng, Z. (2022). Geographical POI recommendation for Internet of Things: A federated learning approach using matrix factorization. Int. J. Commun. Syst., e5161.10.1002/dac.5161 ↗
7. Performance improvement of a movie recommendation system based on personal propensity and secure collaborative filtering10.3745/JIPS.2013.9.1.157 ↗
8. Recommender systems under European AI regulations10.1145/3512728 ↗
9. McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017, January 20–22). Communication-efficient learning of deep networks from decentralized data. Proceedings of the Artificial Intelligence and Statistics, Lauderdale, FL, USA.
10. Yang, L., Tan, B., Zheng, V.W., Chen, K., and Yang, Q. (2020). Federated Learning: Privacy and Incentive, Springer.10.1007/978-3-030-63076-8 ↗
11. Studying the impact of data disclosure mechanism in recommender systems via simulation
12. Anelli, V.W., Di Noia, T., Di Sciascio, E., Ferrara, A., and Mancino, A.C.M. (2022, January 29–30). Addressing Privacy in Recommender Systems with Federated Learning. Proceedings of the IIR2022: 12th Italian Information Retrieval Workshop, Milan, Italy.
13. Zhang, B., Wang, N., and Jin, H. (2014, January 9–11). Privacy concerns in online recommender systems: Influences of control and user data input. Proceedings of the 10th Symposium On Usable Privacy and Security (SOUPS 2014), Menlo Park, CA, USA.
14. Evaluating recommender systems from the user’s perspective: Survey of the state of the art10.1007/s11257-011-9115-7 ↗
15. Explaining the user experience of recommender systems10.1007/s11257-011-9118-4 ↗
16. A federated collaborative recommendation model for privacy-preserving distributed recommender applications based on microservice framework10.1016/j.jpdc.2022.12.002 ↗
17. Yuan, W., Yang, C., Nguyen, Q.V.H., Cui, L., He, T., and Yin, H. (2023). Interaction-level Membership Inference Attack Against Federated Recommender Systems. arXiv.10.1145/3543507.3583359 ↗
18. Zhang, S., and Yin, H. (2022). Comprehensive Privacy Analysis on Federated Recommender System against Attribute Inference Attacks. arXiv.
19. Federated learning: Challenges, methods, and future directions
20. Federated machine learning: Concept and applications10.1145/3339474 ↗
21. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions10.1109/TKDE.2005.99 ↗
22. A survey on security and privacy of federated learning10.1016/j.future.2020.10.007 ↗
23. Lyu, L., Yu, H., Ma, X., Chen, C., Sun, L., Zhao, J., Yang, Q., and Philip, S.Y. (2022). Privacy and robustness in federated learning: Attacks and defenses. IEEE Trans. Neural Netw. Learn. Syst., early access.10.1109/TNNLS.2022.3216981 ↗
24. A federated learning approach for privacy protection in context-aware recommender systems10.1093/comjnl/bxab025 ↗
25. Tan, B., Liu, B., Zheng, V., and Yang, Q. (2020, January 22–26). A federated recommender system for online services. Proceedings of the 14th ACM Conference on Recommender Systems, Virtual Event.10.1145/3383313.3411528 ↗
26. A survey on federated learning10.1016/j.knosys.2021.106775 ↗
27. A secure cloudlet-based charging station recommendation for electric vehicles empowered by federated learning10.1109/TII.2022.3148997 ↗
28. Kalloori, S., and Klingler, S. (October, January 27). Horizontal cross-silo federated recommender systems. Proceedings of the 15th ACM Conference on Recommender Systems, Amsterdam, The Netherlands.
29. Liu, S. (2022). Multi-Dimensional Federated Learning in Recommender Systems. [Ph.D. Thesis, Rutgers University-School of Graduate Studies].
30. Neumann, D., Lutz, A., Müller, K., and Samek, W. (2023). A Privacy Preserving System for Movie Recommendations using Federated Learning. arXiv.10.1145/3634686 ↗
31. Federated matrix factorization for privacy-preserving recommender systems10.1016/j.asoc.2021.107700 ↗
32. Deep learning techniques for recommender systems based on collaborative filtering10.1111/exsy.12647 ↗
33. Federated learning review: Fundamentals, enabling technologies, and future applications10.1016/j.ipm.2022.103061 ↗
34. A trusted recommendation scheme for privacy protection based on federated learning10.1007/s42045-020-00045-8 ↗
35. ReFRS: Resource-efficient federated recommender system for dynamic and diversified user preferences10.1145/3560486 ↗
36. Representation, similarity measures and aggregation methods using fuzzy sets for content-based recommender systems10.1016/j.fss.2008.03.017 ↗
37. Recommendation system using feature extraction and pattern recognition in clinical care systems10.1080/17517575.2018.1557256 ↗
38. Kurt, Z., and Özkan, K. (2017, January 5–8). An image-based recommender system based on feature extraction techniques. Proceedings of the 2017 International Conference on Computer Science and Engineering (UBMK), Antalya, Turkey.10.1109/UBMK.2017.8093527 ↗
39. Recommender systems10.1016/j.physrep.2012.02.006 ↗
40. Jalalirad, A., Scavuzzo, M., Capota, C., and Sprague, M. (2019, January 2–5). A simple and efficient federated recommender system. Proceedings of the 6th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, Auckland, New Zealand.10.1145/3365109.3368788 ↗
41. Anelli, V.W., Deldjoo, Y., Di Noia, T., Ferrara, A., and Narducci, F. (April, January 28). Federank: User controlled feedback with federated recommender systems. Proceedings of the Advances in Information Retrieval: 43rd European Conference on IR Research, ECIR 2021, Virtual Event. Proceedings, Part I 43.10.1007/978-3-030-72113-8_3 ↗
42. Khan, F.K., Flanagan, A., Tan, K.E., Alamgir, Z., and Ammad-Ud-Din, M. (October, January 27). A payload optimization method for federated recommender systems. Proceedings of the 15th ACM Conference on Recommender Systems, Amsterdam, The Netherlands.
43. Jie, Z., Chen, S., Lai, J., Arif, M., and He, Z. (2022). Personalized federated recommendation system with historical parameter clustering. J. Ambient. Intell. Humaniz. Comput., 1–11.10.1007/s12652-022-03709-z ↗
44. Chen, H., Fu, C., and Hu, C. (2022). An efficient and secure recommendation system based on federated matrix factorization in digital economy. Pers. Ubiquitous Comput., 1–12.10.1007/s00779-021-01646-w ↗
45. Huang, M., Li, H., Bai, B., Wang, C., Bai, K., and Wang, F. (2020). A federated multi-view deep learning framework for privacy-preserving recommendations. arXiv.
46. Federated recommenders: Methods, challenges and future10.1007/s10586-022-03644-w ↗
47. A content-based recommender system for computer science publications10.1016/j.knosys.2018.05.001 ↗
48. Privacy-preserving federated learning framework in multimedia courses recommendation10.1007/s11276-021-02854-1 ↗
49. Albayati, A.N.K., and Ortakci, Ö.Ü.Y. (2022, January 9–11). Recommendation Systems on Twitter Data for Marketing Purposes using Content-Based Filtering. Proceedings of the 2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), Ankara, Turkey.10.1109/HORA55278.2022.9799989 ↗
50. FedCKE: Cross-Domain Knowledge Graph Embedding in Federated Learning10.1109/TBDATA.2022.3205705 ↗
51. Eren, M.E., Richards, L.E., Bhattarai, M., Yus, R., Nicholas, C., and Alexandrov, B.S. (2022). FedSPLIT: One-Shot Federated Recommendation System Based on Non-negative Joint Matrix Factorization and Knowledge Distillation. arXiv.
52. Hejazinia, M., Huba, D., Leontiadis, I., Maeng, K., Malek, M., Melis, L., Mironov, I., Nasr, M., Wang, K., and Wu, C.J. (2022). Fel: High capacity learning for recommendation and ranking via federated ensemble learning. arXiv.
53. Wazzeh, M., Ould-Slimane, H., Talhi, C., Mourad, A., and Guizani, M. (2022). Warmup and Transfer Knowledge-Based Federated Learning Approach for IoT Continuous Authentication. arXiv.
54. Evfl: An explainable vertical federated learning for data-oriented artificial intelligence systems10.1016/j.sysarc.2022.102474 ↗
55. Federated neural collaborative filtering10.1016/j.knosys.2022.108441 ↗
56. Federated one-class collaborative filtering via privacy-aware non-sampling matrix factorization10.1016/j.knosys.2022.109441 ↗
57. Eren, M.E., Bhattarai, M., Solovyev, N., Richards, L.E., Yus, R., Nicholas, C., and Alexandrov, B.S. (2022, January 12–14). One-Shot Federated Group Collaborative Filtering. Proceedings of the 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA), Nassau, Bahamas.10.1109/ICMLA55696.2022.00107 ↗
58. User-controlled federated matrix factorization for recommender systems10.1007/s10844-021-00688-z ↗
59. Usst: A two-phase privacy-preserving framework for personalized recommendation with semi-distributed training10.1016/j.ins.2022.05.083 ↗
60. Luo, J., Yi, X., Han, F., and Yang, X. (2022). An efficient privacy-preserving recommender system in wireless networks. Wirel. Netw., 1–12.10.1007/s11276-022-03130-6 ↗
61. Huang, H., Li, R., Liu, J., Zhou, S., Lin, K., and Zheng, Z. (2022, January 10–13). Contextfl: Context-aware federated learning by estimating the training and reporting phases of mobile clients. Proceedings of the 2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS), Bologna, Italy.10.1109/ICDCS54860.2022.00061 ↗
62. Cloudlet Federation Based Context-Aware Federated Learning Approach10.1109/ACCESS.2022.3212550 ↗
63. Chagas, A.B. (2023, March 29). A Recommender System to Support the Development of Context-Aware Intelligent Transportation Systems. Available online: https://repositorio.ufpe.br/handle/123456789/46362.
64. Dynamic context management in context-aware recommender systems10.1016/j.compeleceng.2023.108622 ↗
65. Context-aware online client selection for hierarchical federated learning10.1109/TPDS.2022.3186960 ↗
66. Garcıa-Alonso, J., Murillo, J.M., and Berrocal, J. (2021, January 18–21). Towards Proactive Context-Aware IoT Environments by Means of Federated Learning. Proceedings of the ICWE 2021 Workshops: ICWE 2021 International Workshops, BECS and Invited Papers, Biarritz, France. Revised Selected Papers.
67. Using Federated Learning to Achieve Proactive Context-Aware IoT Environments
68. Progress in context-aware recommender systems—An overview10.1016/j.cosrev.2019.01.001 ↗
69. Automatic recommendation system based on hybrid filtering algorithm10.1007/s10639-021-10643-8 ↗
70. A hybrid recommender system for an online store using a fuzzy expert system10.1016/j.eswa.2022.118565 ↗
71. A Comparative Overview of Hybrid Recommender Systems: Review, Challenges, and Prospects
72. Wu, C., Wu, F., Cao, Y., Huang, Y., and Xie, X. (2021). Fedgnn: Federated graph neural network for privacy-preserving recommendation. arXiv.10.1038/s41467-022-30714-9 ↗
73. Secure federated matrix factorization10.1109/MIS.2020.3014880 ↗
74. From distributed machine learning to federated learning: In the view of data privacy and security10.1002/cpe.6002 ↗
75. Asad, M., Moustafa, A., and Yu, C. (2020). A critical evaluation of privacy and security threats in federated learning. Sensors, 20.10.3390/s20247182 ↗
76. Dash, B., Sharma, P., and Ali, A. (2022). Federated Learning for Privacy-Preserving: A Review of PII Data Analysis in Fintech. Int. J. Softw. Eng. Appl. IJSEA, 13.10.5121/ijsea.2022.13401 ↗
77. FCMF: Federated collective matrix factorization for heterogeneous collaborative filtering10.1016/j.knosys.2021.106946 ↗
78. Federated matrix factorization with privacy guarantee10.14778/3503585.3503598 ↗
79. Truex, S., Liu, L., Chow, K.H., Gursoy, M.E., and Wei, W. (2020, January 27). LDP-Fed: Federated learning with local differential privacy. Proceedings of the Third ACM International Workshop on Edge Systems, Analytics and Networking, Heraklion, Greece.10.1145/3378679.3394533 ↗
80. Zheng, X., Guan, M., Jia, X., Guo, L., and Luo, Y. (2022). A Matrix Factorization Recommendation System-Based Local Differential Privacy for Protecting Users’ Sensitive Data. IEEE Trans. Comput. Soc. Syst., early access.10.1109/TCSS.2022.3170691 ↗
81. An improved matrix factorization with local differential privacy based on piecewise mechanism for recommendation systems10.1016/j.eswa.2022.119457 ↗
82. Preserving user privacy for machine learning: Local differential privacy or federated machine learning?10.1109/MIS.2020.3010335 ↗
83. Federated Learning and Differential Privacy: Software tools analysis, the Sherpa. ai FL framework and methodological guidelines for preserving data privacy10.1016/j.inffus.2020.07.009 ↗
84. Hu, H., Dobbie, G., Salcic, Z., Liu, M., Zhang, J., Lyu, L., and Zhang, X. (2021). Differentially private locality sensitive hashing based federated recommender system. Concurr. Comput. Pract. Exp., e6233.10.1002/cpe.6233 ↗
85. Hou, D., Zhang, J., Ma, J., Zhu, X., and Man, K.L. (2021, January 10–12). Application of Differential Privacy for Collaborative Filtering Based Recommendation System: A Survey. Proceedings of the 2021 12th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), Xi’an, China.10.1109/PAAP54281.2021.9720452 ↗
86. CE-Fed: Communication efficient multi-party computation enabled federated learning10.1016/j.array.2022.100207 ↗
87. Byrd, D., and Polychroniadou, A. (2020, January 15–16). Differentially private secure multi-party computation for federated learning in financial applications. Proceedings of the First ACM International Conference on AI in Finance, New York, NY, USA.10.1145/3383455.3422562 ↗
88. Wang, Y., Tong, Y., and Shi, D. (2020, January 7–12). Federated latent dirichlet allocation: A local differential privacy based framework. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i04.6096 ↗
89. Zhou, J., Feng, Y., Wang, Z., and Guo, D. (2021). Using secure multi-party computation to protect privacy on a permissioned blockchain. Sensors, 21.10.3390/s21041540 ↗
90. An efficient approach for privacy preserving decentralized deep learning models based on secure multi-party computation10.1016/j.neucom.2020.10.014 ↗
91. Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H.B., Patel, S., Ramage, D., Segal, A., and Seth, K. (November, January 30). Practical secure aggregation for privacy-preserving machine learning. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, Dallas, TX, USA.10.1145/3133956.3133982 ↗
92. Data security in recommendation system using homomorphic encryption
93. A homomorphic-encryption-based vertical federated learning scheme for rick management10.2298/CSIS190923022O ↗
94. Mahmood, Z.H., and Ibrahem, M.K. (2018, January 20–21). New fully homomorphic encryption scheme based on multistage partial homomorphic encryption applied in cloud computing. Proceedings of the 2018 1st Annual International Conference on Information and Sciences (AiCIS), Fallujah, Iraq.10.1109/AiCIS.2018.00043 ↗
95. Kim, S., Kim, J., Koo, D., Kim, Y., Yoon, H., and Shin, J. (3, January 30). Efficient privacy-preserving matrix factorization via fully homomorphic encryption. Proceedings of the 11th ACM on Asia Conference on Computer and Communications Security, Xi’an, China.
96. Badsha, S., Yi, X., Khalil, I., and Bertino, E. (2017, January 5–8). Privacy preserving user-based recommender system. Proceedings of the 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS), Atlanta, GA, USA.10.1109/ICDCS.2017.248 ↗
97. Wang, L., Wang, Y., Bai, Y., Liu, P., and Li, X. (2021, January 9–12). POI recommendation with federated learning and privacy preserving in cross domain recommendation. Proceedings of the IEEE INFOCOM 2021-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), Virtual.10.1109/INFOCOMWKSHPS51825.2021.9484510 ↗
98. Zhang, S., Li, Z., Chen, Q., Zheng, W., Leng, J., and Guo, M. (2021, January 9–12). Dubhe: Towards data unbiasedness with homomorphic encryption in federated learning client selection. Proceedings of the 50th International Conference on Parallel Processing, Lemont, IL, USA.10.1145/3472456.3473513 ↗
99. Han, J., Khan, A.F., Zawad, S., Anwar, A., Angel, N.B., Zhou, Y., Yan, F., and Butt, A.R. (2022, January 15–20). Tokenized incentive for federated learning. Proceedings of the Federated Learning Workshop at the Association for the Advancement of Artificial Intelligence (AAAI) Conference, Qinghai, China.10.1109/CLOUD55607.2022.00064 ↗
100. Bagdasaryan, E., Song, C., van Dalen, R., Seigel, M., and Cahill, Á. (2022). Training a Tokenizer for Free with Private Federated Learning. arXiv.