Federated Recommendation via Stochastic Aggregation and Consistency Inference
Open Access
- 25 March 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (3) , 1-40
Abstract
With growing concerns over user privacy, federated recommendation (FedRec) has emerged as a mainstream solution for personalized recommendation services. FedRec trains user-private parameters on local clients while collaboratively updating global parameters on a centralized server. However, despite advances in optimizing these local and global parameters, existing methods overlook two key challenges: tradeoff training and distribution discrepancy . Tradeoff training balances timely local updates with diverse global parameters, limiting the model’s learning ability. Distribution discrepancy arises from the divergence between locally trained global parameters and those aggregated by the server, corrupting inference performance. To fill in the gap, we propose FedSC , a principled federated recommendation framework that boosts FedRec’s training and inference processes with minimal yet nontrivial efforts. During training, FedSC employs a stochastic aggregation strategy where all users participate in every round, while only a random subset is selected for aggregation, preserving the diversity of global parameters and ensuring timely local updates. During inference, FedSC makes recommendations with a consistency inference mechanism that uses the most recent locally trained global parameters of each user to improve the model’s understanding of user preferences. Extensive experiments on multiple benchmark datasets demonstrate the superiority of FedSC, achieving up to a 20% improvement in most evaluation scenarios.Keywords
Funding Information
- National Natural Science Foundation of China (62432006 and 62531013)
- shandong provincial key research and development program (2023CXGC010112)
- Shandong Provincial Natural Science Foundation (ZR2024JQ001 and ZR2025LZH004)
- Taishan Scholars Program (tsqn202306007 and tsqn202408317)
This publication has 36 references indexed in Scilit:
- FedCORE: Federated Learning for Cross-Organization Recommendation EcosystemIEEE Transactions on Knowledge and Data Engineering, 2024
- A Survey on Federated Recommendation SystemsIEEE Transactions on Neural Networks and Learning Systems, 2024
- Comprehensive Privacy Analysis on Federated Recommender System Against Attribute Inference AttacksIEEE Transactions on Knowledge and Data Engineering, 2023
- Privacy-Preserving and Byzantine-Robust Federated LearningIEEE Transactions on Dependable and Secure Computing, 2023
- Personalized Federated Few-Shot LearningIEEE Transactions on Neural Networks and Learning Systems, 2022
- A federated graph neural network framework for privacy-preserving personalizationNature Communications, 2022
- Federated Neural Collaborative FilteringKnowledge-Based Systems, 2022
- Secure Federated Matrix FactorizationIEEE Intelligent Systems, 2020
- Federated Learning With Differential Privacy: Algorithms and Performance AnalysisIEEE Transactions on Information Forensics and Security, 2020
- Matrix Factorization Techniques for Recommender SystemsComputer, 2009