Personalized Federated Recommendation for Cold-Start Users via Adaptive Knowledge Fusion

Federated Recommendation System (FRS) usually offers recommendation services for users while keeping their data locally to ensure privacy. Currently, most FRS literature assumes that fixed users participate in federated training with personal IoT devices (e.g., mobile phones and PC). However, users may join incrementally, and retraining the entire FRS for each new participating user is unfeasible due to the high training costs and the limited global knowledge contribution from a small number of new users. To guarantee the quality service for these new users, we take a dive into the federated recommendation for cold-start users, a novel scenario where the new participating users can directly obtain a promising recommendation without comprehensive training with all participating users by leveraging both transferred knowledge from the converged warm clients and the knowledge learned from the local data. Nevertheless, the efficient transfer of knowledge from warm clients remains controversial. On the one hand, cold clients may introduce new sparse items, resulting in a shift in the item embedding distribution compared to that converged on warm clients. On the other hand, cold-start users need to match similar user information from warm clients for a collaborative recommendation, but directly sharing user information is a violation of privacy and unacceptable. To tackle these challenges, we propose an efficient and privacy-enhanced federated recommendation for cold-start users (FR-CSU) that each client can adaptively transfer both user and item knowledge separately from warm clients and implement recommendations with local and transferred knowledge fusion. Specifically, each cold client will train a mapping function locally to transfer the aligned item embedding. Meanwhile, warm clients will maintain a user prototype network collaboratively that provides privacy-friendly yet effective user information for cold-start users. Then, a linear function system will integrate the transferred and local knowledge to improve recommendations. Extensive experiments show that FR-CSU achieves superior performance compared to state-of-the-art methods.