FedPop: A Bayesian Approach for Personalised Federated Learning
Personalised federated learning (FL) aims at collaboratively learning a machine learning model taylored for each client. Albeit promising advances have been made in this direction, most of existing approaches works do not allow for uncertainty quantification which is crucial in many applications. In addition, personalisation in the cross-device setting still involves important issues, especially for new clients or those having small number of observations. This paper aims at filling these gaps. To this end, we propose a novel methodology coined FedPop by recasting personalised FL into the population modeling paradigm where clients' models involve fixed common population parameters and random effects, aiming at explaining data heterogeneity. To derive convergence guarantees for our scheme, we introduce a new class of federated stochastic optimisation algorithms which relies on Markov chain Monte Carlo methods. Compared to existing personalised FL methods, the proposed methodology has important benefits: it is robust to client drift, practical for inference on new clients, and above all, enables uncertainty quantification under mild computational and memory overheads. We provide non-asymptotic convergence guarantees for the proposed algorithms and illustrate their performances on various personalised federated learning tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningUncertainty QuantificationSimilar Papers 제목 키워드 기반
FedPoP: Federated Learning Meets Proof of Participation
Federated learning (FL) offers privacy preserving, distributed machine learning, allowing clients to contribute to a global model without revealing their local data. As models increasingly serve as monetizable digital as…
Federated LearningFedPop: Federated Population-based Hyperparameter Tuning
Federated Learning (FL) is a distributed machine learning (ML) paradigm, in which multiple clients collaboratively train ML models without centralizing their local data. Similar to conventional ML pipelines, the client l…
Computational EfficiencyEvolutionary AlgorithmsFederated LearningA novel parameter decoupling approach of personalized federated learning for image analysis
Given the importance of privacy protection in databases and other institutions, federated learning (FL) is used to benefit training machine learning models based on these decentralised and private data so as to address t…
Federated LearningPersonalized Federated LearningFedCARE: A Multi-Objective Personalised Federated Learning Framework for Smart Healthcare
Federated Learning (FL) enables collaborative model training across distributed healthcare institutions without centralising sensitive patient data. However, real-world healthcare federations are often characterised not …
Federated LearningFederated Learning with Nonvacuous Generalisation Bounds
We introduce a novel strategy to train randomised predictors in federated learning, where each node of the network aims at preserving its privacy by releasing a local predictor but keeping secret its training dataset wit…
Federated Learning