Horizontal Federated Recommender System: A Survey

Abstract

Due to underlying privacy-sensitive information in user-item interaction data, the risk of privacy leakage exists in the centralized-training recommender system (RecSys). To this issue, federated learning, a privacy-oriented distributed computing paradigm, is introduced and promotes the crossing field “Federated Recommender System (FedRec).” Regarding data distribution characteristics, there are horizontal, vertical, and transfer variants, where horizontal FedRec (HFedRec) occupies a dominant position. User devices can personally participate in the horizontal federated architecture, making user-level privacy feasible. Therefore, we target the horizontal point and summarize existing works more elaborately than existing FedRec surveys. First, from the model perspective, we group them into different learning paradigms (e.g., deep learning and meta learning). Second, from the privacy perspective, privacy-preserving techniques are systematically organized (e.g., homomorphic encryption and differential privacy). Third, from the federated perspective, fundamental issues (e.g., communication and fairness) are discussed. Fourth, each perspective has detailed subcategories, and we specifically state their unique challenges with the observation of current progress. Finally, we figure out potential issues and promising directions for future research.