PPFL: A Personalized Federated Learning Framework for Heterogeneous Population
Not on the map. Why?
Abstract (arXiv)
Personalization aims to characterize individual preferences and is widely applied across many fields. However, conventional personalized methods operate in a centralized manner, potentially exposing raw data when pooling individual information. In this paper, with privacy considerations, we develop a flexible and interpretable personalized framework within the paradigm of federated learning, called textttPPFL (Population Personalized Federated Learning). By leveraging ``canonical models" to capture fundamental characteristics of a heterogeneous population and employing ``membership vectors" to reveal clients' preferences, textttPPFL models heterogeneity as clients' varying preferences for these characteristics. This approach provides substantial insights into client characteristics, which are lacking in existing Personalized Federated Learning (PFL) methods. Furthermore, we explore the relationship between textttPPFL and three main branches of PFL methods: clustered FL, multi-task PFL, and decoupling PFL, and demonstrate the advantages of textttPPFL. To solve textttPPFL (a non-convex optimization problem with linear constraints), we propose a novel random block coordinate descent algorithm and establish its convergence properties. We conduct experiments on both pathological and practical data sets, and the results validate the effectiveness of textttPPFL.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 43 of its 78 references that are in the map. First posted on arXiv 22 Oct 2023.
Builds on
43 of 78 references.
References · 43
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
- 2018LEAF: A Benchmark for Federated Settingscited by 780
- 2017Federated Multi-Task Learningcited by 669
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
- 2020Personalized Federated Learning with Moreau Envelopescited by 612
31 more
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
- 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
- 2020An Efficient Framework for Clustered Federated Learningcited by 505
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
- 2021Towards Personalized Federated Learningcited by 462
- 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
- 2019Interpretable machine learning: definitions, methods, and applicationscited by 303
- 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
- 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
- 2022Federated Learning with Partial Model Personalizationcited by 114
- 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 112
- 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 108
- 2020TiFL: A Tier-based Federated Learning Systemcited by 95
- 2020Laplacian Regularized Few-Shot Learningcited by 90
- 2022Personalized Federated Learning via Variational Bayesian Inferencecited by 68
- 2022Federated Learning via Inexact ADMMcited by 44
- 2022FedPop: A Bayesian Approach for Personalised Federated Learningcited by 35
- 2021Personalized Federated Learning: A Unified Framework and Universal Optimization Techniquescited by 34
- 2022LightFR: Lightweight Federated Recommendation with Privacy-preserving Matrix Factorizationcited by 26
- 2023Bayesian Federated Learning: A Surveycited by 22
- 2023Dual Personalization on Federated Recommendationcited by 19
- 2021PFA: Privacy-preserving Federated Adaptation for Effective Model Personalizationcited by 18
- 2021Federated Learning from Small Datasetscited by 14
- 2013Stochastic Block Mirror Descent Methods for Nonsmooth and Stochastic Optimizationcited by 12
- 2020Federated Block Coordinate Descent Scheme for Learning Global and Personalized Modelscited by 11
- 2022Federated Data Analytics: A Study on Linear Modelscited by 9
- 2022FedDAR: Federated Domain-Aware Representation Learningcited by 8
- 2019A Distributed Method for Fitting Laplacian Regularized Stratified Modelscited by 7
- 2023Federated Learning of Shareable Bases for Personalization-Friendly Image Classificationcited by 6
- 2018Distributed Majorization-Minimization for Laplacian Regularized Problemscited by 4
- 2021Federated Learning Algorithms for Generalized Mixed-effects Model (GLMM) on Horizontally Partitioned Data from Distributed Sourcescited by 4
Built on by
Citing papers per year: 2024: 1.
1 paper.