Federated recommendation improves by learning hierarchical client usefulness
FedHUR: Learning Hierarchical Utility-Guided Client Relations for Personalized Federated Recommendation
Information Retrieval
Summary
Federated recommendation lets many devices work together to create better personalized suggestions without sharing private user data. Existing methods combine information from clients based on fixed assumptions about similarity, but this often misses complex relationships and which clients really help improve recommendations. The authors propose FedHUR, which groups client data hierarchically and learns how useful other clients’ information is for each device’s predictions. This approach better captures multi-level relationships and selectively uses helpful information, improving recommendation quality on several real-world datasets.
What this means in practice
- •For mobile app developers: Enhance federated recommendation models on user devices by selectively aggregating useful client data using hierarchical relations for better personalized suggestions.
- •For ecommerce platform teams: Improve product recommendation quality across distributed user data without compromising privacy by incorporating hierarchical utility-guided client relations in federated training.
Authors
Mingzhe Han, Jiahao Liu, Dongsheng Li, Jiankui Zhou, Hansu Gu, Peng Zhang, Ning Gu, Tun Lu
Abstract
Federated recommendation enables collaborative model training while keeping user interaction data on local clients. A central problem in federated recommendation is how to aggregate useful information across clients for personalized recommendation. Existing personalized aggregation methods usually construct client relations from predefined parameter-based assumptions, such as parameter similarity or complementarity, and use these relations to determine aggregation weights. However, such methods construct a single global relation, which is insufficient to capture the hierarchical and multi-granularity nature of user relations in recommendation. Moreover, these predefined relations cannot directly reflect whether the related clients can improve prediction performance after aggregation. To address these limitations, we propose FedHUR, a federated recommendation framework for learning hierarchical utility-guided client relations. FedHUR takes item-item filters as the object for relation construction and aggregation. Specifically, it first aggregates and clusters each client's local information to obtain global hierarchical information. Each client computes hierarchical utility signals based on its local information and the global hierarchical information, indicating which collaborative information is useful for improving its prediction. The server uses these utility signals to retrieve clients that are useful to that client for further personalized aggregation. Extensive experiments on five real-world datasets show that FedHUR consistently outperforms existing federated recommendation baselines, demonstrating the effectiveness of hierarchical utility-guided client relation learning. Code is available at https://github.com/Mingzhe-Han/FedHUR.