A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directions

2025-08-27

AI Summary

Existing federated recommendation research predominantly adopts a federated learning perspective, overlooking recommendation-specific modeling requirements and practical deployment challenges—leading to a significant theory–practice gap. Method: This paper pioneers a recommendation-system-centric approach, proposing a “scenario–architecture” co-analysis framework that rigorously distinguishes inherent recommendation challenges (e.g., data sparsity, temporal dynamics) from those introduced by federated architectures (e.g., statistical heterogeneity, communication overhead). It systematically surveys methodological evolution, bottlenecks, and optimization strategies across key scenarios—including cross-domain recommendation, heterogeneous data modeling, and distributed aggregation—and derives privacy-preserving, production-ready deployment guidelines. Contribution/Results: The work bridges the longstanding gap between theoretical advances in federated learning and industrial-scale recommendation deployment, offering both conceptual clarity and actionable insights for real-world federated recommender systems.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Data Mining & Knowledge Management: Recommender Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Extending recommender systems to federated learning (FL) frameworks to protect the privacy of users or platforms while making recommendations has recently gained widespread attention in academia. This is due to the natural coupling of recommender systems and federated learning architectures: the data originates from distributed clients (mostly mobile devices held by users), which are highly related to privacy. In a centralized recommender system (CenRec), the central server collects clients' data, trains the model, and provides the service. Whereas in federated recommender systems (FedRec), the step of data collecting is omitted, and the step of model training is offloaded to each client. The server only aggregates the model and other knowledge, thus avoiding client privacy leakage. Some surveys of federated recommender systems discuss and analyze related work from the perspective of designing FL systems. However, their utility drops by ignoring specific recommendation scenarios' unique characteristics and practical challenges. For example, the statistical heterogeneity issue in cross-domain FedRec originates from the label drift of the data held by different platforms, which is mainly caused by the recommender itself, but not the federated architecture. Therefore, it should focus more on solving specific problems in real-world recommendation scenarios to encourage the deployment FedRec. To this end, this review comprehensively analyzes the coupling of recommender systems and federated learning from the perspective of recommendation researchers and practitioners. We establish a clear link between recommendation scenarios and FL frameworks, systematically analyzing scenario-specific approaches, practical challenges, and potential opportunities. We aim to develop guidance for the real-world deployment of FedRec, bridging the gap between existing research and applications.

Problem

• Surveying techniques for privacy-preserving federated recommender systems
• Addressing practical challenges in cross-domain recommendation scenarios
• Bridging research gaps for real-world FedRec deployment

Innovation

• Federated learning for privacy protection
• Client-side model training aggregation
• Scenario-specific FL recommendation frameworks