Communication-Efficient Personalized Adaptation via Federated-Local Model Merging

• URL: http://arxiv.org/abs/2602.18658v1
• Date: Fri, 20 Feb 2026 23:29:28 GMT
• Title: Communication-Efficient Personalized Adaptation via Federated-Local Model Merging
• Authors: Yinan Zou, Md Kamran Chowdhury Shisher, Christopher G. Brinton, Vishrant Tripathi,
• Abstract summary: Potara is a principled framework for federated personalization.<n>It constructs a personalized model for each client by merging two complementary models.<n>Experiments on vision and language benchmarks show that Potara consistently improves personalization while reducing communication.
• Score: 24.80216233896655
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Parameter-efficient fine-tuning methods, such as LoRA, offer a practical way to adapt large vision and language models to client tasks. However, this becomes particularly challenging under task-level heterogeneity in federated deployments. In this regime, personalization requires balancing general knowledge with personalized knowledge, yet existing approaches largely rely on heuristic mixing rules and lack theoretical justification. Moreover, prior model merging approaches are also computation and communication intensive, making the process inefficient in federated settings. In this work, we propose Potara, a principled framework for federated personalization that constructs a personalized model for each client by merging two complementary models: (i) a federated model capturing general knowledge, and (ii) a local model capturing personalized knowledge. Through the construct of linear mode connectivity, we show that the expected task loss admits a variance trace upper bound, whose minimization yields closed-form optimal mixing weights that guarantee a tighter bound for the merged model than for either the federated or local model alone. Experiments on vision and language benchmarks show that Potara consistently improves personalization while reducing communication, leading to a strong performance-communication trade-off.

Related papers

• Model Merging via Multi-Teacher Knowledge Distillation [11.543771846135021]
  We introduce a novel flatness-aware PAC-Bayes generalization bound specifically for the model merging setting.<n>We frame model merging as multi-teacher knowledge distillation on scarce, unlabeled data.<n>We formally demonstrate that minimizing the student-teacher Kullback-Leibler divergence directly tightens the upper bound on the merged model's excess risk.
  arXiv  Detail & Related papers  (2025-12-24T17:10:44Z)
• CO-PFL: Contribution-Oriented Personalized Federated Learning for Heterogeneous Networks [51.43780477302533]
  Contribution-Oriented PFL (CO-PFL) is a novel algorithm that dynamically estimates each client's contribution for global aggregation.<n>CO-PFL consistently surpasses state-of-the-art methods in robustness in personalization accuracy, robustness, scalability and convergence stability.
  arXiv  Detail & Related papers  (2025-10-23T05:10:06Z)
• NAN: A Training-Free Solution to Coefficient Estimation in Model Merging [61.36020737229637]
  We show that the optimal merging weights should scale with the amount of task-specific information encoded in each model.<n>We propose NAN, a simple yet effective method that estimates model merging coefficients via the inverse of parameter norm.<n>NAN is training-free, plug-and-play, and applicable to a wide range of merging strategies.
  arXiv  Detail & Related papers  (2025-05-22T02:46:08Z)
• 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)
• Decentralized Directed Collaboration for Personalized Federated Learning [39.29794569421094]
  We concentrate on the Decentralized Personalized Learning (DPFL) that performs distributed training model computation. We propose a directed collaboration framework by incorporating textbfDecentralized textbfFederated textbfPartial textbfGradient textbfPedGP.
  arXiv  Detail & Related papers  (2024-05-28T06:52:19Z)
• Towards More Suitable Personalization in Federated Learning via Decentralized Partial Model Training [67.67045085186797]
  Almost all existing systems have to face large communication burdens if the central FL server fails. It personalizes the "right" in the deep models by alternately updating the shared and personal parameters. To further promote the shared parameters aggregation process, we propose DFed integrating the local Sharpness Miniization.
  arXiv  Detail & Related papers  (2023-05-24T13:52:18Z)
• Personalizing Federated Learning with Over-the-Air Computations [84.8089761800994]
  Federated edge learning is a promising technology to deploy intelligence at the edge of wireless networks in a privacy-preserving manner. Under such a setting, multiple clients collaboratively train a global generic model under the coordination of an edge server. This paper presents a distributed training paradigm that employs analog over-the-air computation to address the communication bottleneck.
  arXiv  Detail & Related papers  (2023-02-24T08:41:19Z)
• PersA-FL: Personalized Asynchronous Federated Learning [1.1838866556981258]
  We study the personalized federated learning problem under asynchronous updates. In this problem, each client seeks to obtain a personalized model that simultaneously outperforms local and global models. We consider two optimization-based frameworks for personalization.
  arXiv  Detail & Related papers  (2022-10-03T18:44:28Z)
• FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning [87.08902493524556]
  Federated learning(FL) has recently attracted increasing attention from academia and industry. We propose FedDM to build the global training objective from multiple local surrogate functions. In detail, we construct synthetic sets of data on each client to locally match the loss landscape from original data.
  arXiv  Detail & Related papers  (2022-07-20T04:55:18Z)
• Adaptive Personalized Federated Learning [20.80073507382737]
  Investigation of the degree of personalization in federated learning algorithms has shown that only maximizing the performance of the global model will train the capacity of the local models to personalize.
  arXiv  Detail & Related papers  (2020-03-30T13:19:37Z)

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.