Federated recommender system with data valuation for E-commerce platform

Federated Learning (FL) is gaining prominence in machine learning as privacy concerns grow. This paradigm allows each client (e.g., an individual online store) to train a recommendation model locally while sharing only model updates, without exposing the raw interaction logs to a central server, thereby preserving privacy in a decentralized environment. Nonetheless, despite the abundance of publicly available datasets that could substantially enrich local training, most existing FL-based recommender systems continue to rely only on private client data, leaving this potential largely unexplored. To this end, we consider a realistic scenario wherein a large shopping platform collaborates with multiple small online stores to build a global recommender system. The platform possesses global data, such as shareable user and item lists, while each store holds a portion of interaction data privately (or locally). Although integrating global data can help mitigate the limitations of sparse and biased clients’ local data, it also introduces additional challenges: simply combining all global interactions can amplify noise and irrelevant patterns, degrading personalization and increasing computational costs. To address these challenges, we propose, which selectively augments each client’s local graph with semantically aligned samples from the global dataset. employs: (i) a pre-trained graph encoder to extract global structural features, (ii) a local valid predictor to assess the client-specific relevance, and (iii) a reinforcement-learning-based probability estimator to filter and sample only the most pertinent global interactions. improves performance by up to 34.86% on recognized benchmarks in FL environments.