Federated Multi-view Matrix Factorization for Personalized Recommendations

Abstract

We introduce the federated multi-view matrix factorization method that extends the federated learning framework to matrix factorization with multiple data sources. Our method is able to learn the multi-view model without transferring the user's personal data to a central server. As far as we are aware this is the first federated model to provide recommendations using multi-view matrix factorization. The model is rigorously evaluated on three datasets on production settings. Empirical validation confirms that federated multi-view matrix factorization outperforms simpler methods that do not take into account the multi-view structure of the data, in addition, it demonstrates the usefulness of the proposed method for the challenging prediction tasks of cold-start federated recommendations.

arXiv comment16 pages, 3 figures, 5 tables, submitted to a conference

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Practical Bayesian Optimization of Machine Learning Algorithms
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• An overview of gradient descent optimization algorithms
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Towards Federated Learning at Scale: System Design
• Secure Federated Transfer Learning
• Federated Machine Learning: Concept and Applications
• Secure Federated Matrix Factorization
• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System
• Sparse group factor analysis for biclustering of multiple data sources
• Scalable Probabilistic Matrix Factorization with Graph-Based Priors
• Cold-start recommendations in Collective Matrix Factorization
• Kernelized Bayesian Matrix Factorization

Cited by in corpus (11)

• FedML: A Research Library and Benchmark for Federated Machine Learning
• FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
• Federated Social Recommendation with Graph Neural Network
• FedMood: Federated Learning on Mobile Health Data for Mood Detection
• Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources
• A Privacy Preserving System for Movie Recommendations Using Federated Learning
• Federated Reconstruction: Partially Local Federated Learning
• A Federated Multi-View Deep Learning Framework for Privacy-Preserving Recommendations
• Fast-adapting and Privacy-preserving Federated Recommender System
• PrivMVMF: Privacy-Preserving Multi-View Matrix Factorization for Recommender Systems
• Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving