Few-for-Many Personalized Federated Learning

• URL: http://arxiv.org/abs/2603.11992v1
• Date: Thu, 12 Mar 2026 14:43:46 GMT
• Title: Few-for-Many Personalized Federated Learning
• Abstract summary: FedFew is a practical algorithm that jointly optimize the $K$ server models through efficient gradient-based updates.<n>Experiments across vision, NLP, and real-world medical datasets demonstrate that FedFew, with just 3 models, consistently outperforms other state-of-the-art approaches.
• Score: 21.377573928351833
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Personalized Federated Learning (PFL) aims to train customized models for clients with highly heterogeneous data distributions while preserving data privacy. Existing approaches often rely on heuristics like clustering or model interpolation, which lack principled mechanisms for balancing heterogeneous client objectives. Serving $M$ clients with distinct data distributions is inherently a multi-objective optimization problem, where achieving optimal personalization ideally requires $M$ distinct models on the Pareto front. However, maintaining $M$ separate models poses significant scalability challenges in federated settings with hundreds or thousands of clients. To address this challenge, we reformulate PFL as a few-for-many optimization problem that maintains only $K$ shared server models ($K \ll M$) to collectively serve all $M$ clients. We prove that this framework achieves near-optimal personalization: the approximation error diminishes as $K$ increases and each client's model converges to each client's optimum as data grows. Building on this reformulation, we propose FedFew, a practical algorithm that jointly optimizes the $K$ server models through efficient gradient-based updates. Unlike clustering-based approaches that require manual client partitioning or interpolation-based methods that demand careful hyperparameter tuning, FedFew automatically discovers the optimal model diversity through its optimization process. Experiments across vision, NLP, and real-world medical imaging datasets demonstrate that FedFew, with just 3 models, consistently outperforms other state-of-the-art approaches. Code is available at https://github.com/pgg3/FedFew.

Related papers

• FedPPA: Progressive Parameter Alignment for Personalized Federated Learning [0.9931624906346306]
  Federated Learning (FL) is designed as a decentralized, privacy-preserving machine learning paradigm that enables multiple clients to collaboratively train a model without sharing their data.<n>In real-world scenarios, clients often have heterogeneous computational resources and hold non-independent and identically distributed data (non-IID), which poses significant challenges during training.<n>We propose Progressive Alignment (FedPPA), which progressively aligns the weights of common layers across clients with the global model's weights.<n>Experiments on three image classification datasets, including MNIST, FMNIST, and CIFAR-10, demonstrate that FedPPA consistently outperforms existing FL algorithms,
  arXiv  Detail & Related papers  (2025-10-16T14:03:05Z)
• Not All Clients Are Equal: Collaborative Model Personalization on Heterogeneous Multi-Modal Clients [59.52341877720199]
  We propose FedMosaic, a method that enables knowledge sharing across heterogeneous architectures without huge computational cost.<n>To mimic the real-world task diversity, we propose a multi-modal PFL benchmark spanning 40 distinct tasks with distribution shifts over time.<n>The empirical study shows that FedMosaic outperforms the state-of-the-art PFL methods.
  arXiv  Detail & Related papers  (2025-05-20T09:17:07Z)
• FedMerge: Federated Personalization via Model Merging [51.12769696559237]
  One global model might not be sufficient to serve many clients with non-IID tasks and distributions.<n>We propose a novel FedMerge'' approach that can create a personalized model per client by simply merging multiple global models.<n>We evaluate FedMerge on three different non-IID settings applied to different domains with diverse tasks and data types.
  arXiv  Detail & Related papers  (2025-04-09T10:44:14Z)
• FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clients [25.847042398060616]
  Federated Learning (FL) facilitates collaborative training of a shared global model without exposing clients' private data.<n>We propose FedConv, a client-friendly FL framework, which minimizes the computation and memory burden on resource-constrained clients.<n>We show that FedConv outperforms state-of-the-art FL systems in terms of model accuracy, computation and communication overhead.
  arXiv  Detail & Related papers  (2025-02-28T01:39:53Z)
• Client-Centric Federated Adaptive Optimization [78.30827455292827]
  Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private.<n>We propose Federated-Centric Adaptive Optimization, which is a class of novel federated optimization approaches.
  arXiv  Detail & Related papers  (2025-01-17T04:00:50Z)
• FedSheafHN: Personalized Federated Learning on Graph-structured Data [22.825083541211168]
  We propose a model called FedSheafHN, which embeds each client's local subgraph into a server-constructed collaboration graph. Our model improves the integration and interpretation of complex client characteristics. It also has fast model convergence and effective new clients generalization.
  arXiv  Detail & Related papers  (2024-05-25T04:51:41Z)
• Learn What You Need in Personalized Federated Learning [53.83081622573734]
  $textitLearn2pFed$ is a novel algorithm-unrolling-based personalized federated learning framework. We show that $textitLearn2pFed$ significantly outperforms previous personalized federated learning methods.
  arXiv  Detail & Related papers  (2024-01-16T12:45:15Z)
• FedDWA: Personalized Federated Learning with Dynamic Weight Adjustment [20.72576355616359]
  We propose a new PFL algorithm called emphFedDWA (Federated Learning with Dynamic Weight Adjustment) to address the problem. FedDWA computes personalized aggregation weights based on collected models from clients. We conduct extensive experiments using five real datasets and the results demonstrate that FedDWA can significantly reduce the communication traffic and achieve much higher model accuracy than the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2023-05-10T13:12:07Z)
• QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning [8.420943739336067]
  federated learning (FL) aims to train a single global model while collaboratively using multiple clients and a server. We introduce a textitquantized and textitpersonalized FL algorithm QuPeD that facilitates collective (personalized model compression) training. Numerically, we validate that QuPeD outperforms competing personalized FL methods, FedAvg, and local training of clients in various heterogeneous settings.
  arXiv  Detail & Related papers  (2021-07-29T10:55:45Z)
• A Bayesian Federated Learning Framework with Online Laplace Approximation [144.7345013348257]
  Federated learning allows multiple clients to collaboratively learn a globally shared model. We propose a novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side. We achieve state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.
  arXiv  Detail & Related papers  (2021-02-03T08:36:58Z)
• Personalized Federated Learning with First Order Model Optimization [76.81546598985159]
  We propose an alternative to federated learning, where each client federates with other relevant clients to obtain a stronger model per client-specific objectives. We do not assume knowledge of underlying data distributions or client similarities, and allow each client to optimize for arbitrary target distributions of interest. Our method outperforms existing alternatives, while also enabling new features for personalized FL such as transfer outside of local data distributions.
  arXiv  Detail & Related papers  (2020-12-15T19:30:29Z)
• Federated Mutual Learning [65.46254760557073]
  Federated Mutual Leaning (FML) allows clients training a generalized model collaboratively and a personalized model independently. The experiments show that FML can achieve better performance than alternatives in typical Federated learning setting.
  arXiv  Detail & Related papers  (2020-06-27T09:35:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.