Personalized Recommendation Models in Federated Settings: A Survey
It tackles the problem of enhancing personalized recommendations while preserving privacy in federated settings for researchers and practitioners, but it is incremental as a survey consolidating existing work.
This survey addresses the underexplored area of user personalization modeling in federated recommender systems, which is crucial for capturing heterogeneous preferences in decentralized and non-IID data settings, by systematically charting its evolution and synthesizing methodologies to overcome technical hurdles.
Federated recommender systems (FedRecSys) have emerged as a pivotal solution for privacy-aware recommendations, balancing growing demands for data security and personalized experiences. Current research efforts predominantly concentrate on adapting traditional recommendation architectures to federated environments, optimizing communication efficiency, and mitigating security vulnerabilities. However, user personalization modeling, which is essential for capturing heterogeneous preferences in this decentralized and non-IID data setting, remains underexplored. This survey addresses this gap by systematically exploring personalization in FedRecSys, charting its evolution from centralized paradigms to federated-specific innovations. We establish a foundational definition of personalization in a federated setting, emphasizing personalized models as a critical solution for capturing fine-grained user preferences. The work critically examines the technical hurdles of building personalized FedRecSys and synthesizes promising methodologies to meet these challenges. As the first consolidated study in this domain, this survey serves as both a technical reference and a catalyst for advancing personalized FedRecSys research.