Federated Context-Aware Personalized Recommendation

Federated recommender system is emerging as a new paradigm for providing personalized services while preserving the privacy of user data. Most existing personalized federated recommender systems predict the user's next item by discretely training user and item embeddings. However, this training approach often overlooks the user's behavioral patterns, suffers from low interpretability, and requires a substantial amount of data and highly meticulous fine-tuning to achieve stable and accurate embeddings. To address these limitations, we propose Federated Context-Aware Personalized Recommendation (FedCAR ), a novel framework that effectively leverages users' recent interactions as behavioral context to guide prediction. Instead of static user embeddings, FedCAR dynamically constructs context representations by aggregating and weighting recently interacted item embeddings. Additionally, we incorporate a contrastive learning strategy that enables the model to capture shared behavioral structures across clients while maintaining personalized preferences, thereby enhancing both generalization and robustness in heterogeneous settings. Experiments on 5 benchmark datasets show that FedCAR outperforms state-of-theart methods and provides interpretable recommendations by explicitly modeling context dependencies.