Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning
Large-scale machine learning systems often involve data distributed across a collection of users. Federated learning algorithms leverage this structure by communicating model updates to a central server, rather than entire datasets. In this paper, we study stochastic optimization algorithms for a personalized federated learning setting involving local and global models subject to user-level (joint) differential privacy. While learning a private global model induces a cost of privacy, local learning is perfectly private. We provide generalization guarantees showing that coordinating local learning with private centralized learning yields a generically useful and improved tradeoff between accuracy and privacy. We illustrate our theoretical results with experiments on synthetic and real-world datasets.
Code (1)
Tasks
Federated LearningPersonalized Federated LearningStochastic OptimizationSimilar Papers 제목 키워드 기반
Differentially Private Federated Clustering with Random Rebalancing
Federated clustering aims to group similar clients into clusters and produce one model for each cluster. Such a personalization approach typically improves model performance compared with training a single model to serve…
Federated User Representation Learning
Collaborative personalization, such as through learned user representations (embeddings), can improve the prediction accuracy of neural-network-based models significantly. We propose Federated User Representation Learnin…
Federated LearningPrivacy PreservingRepresentation LearningA federated graph neural network framework for privacy-preserving personalization
Graph neural network (GNN) is effective in modeling high-order interactions and has been widely used in various personalized applications such as recommendation. However, mainstream personalization methods rely on centra…
Federated LearningGraph Neural NetworkPrivacy PreservingRecommendation SystemsPrototype-Aligned Federated Soft-Prompts for Continual Web Personalization
Continual web personalization is essential for engagement, yet real-world non-stationarity and privacy constraints make it hard to adapt quickly without forgetting long-term preferences. We target this gap by seeking a p…
Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
Multimodal Large Language Models (LLMs) are pivotal in revolutionizing customer support and operations by integrating multiple modalities such as text, images, and audio. Federated Prompt Learning (FPL) is a recently pro…
Federated LearningPrivacy PreservingPrompt Learning