Skip to content
AI News HubLIVE
Original source2 min read

FedSPC: Shared Parameter Correction for Personalized Federated Learning

Summary

FedSPC introduces a modular correction method that applies control-variate correction only to shared parameters in personalized federated learning, improving representative PFL methods like FedPer, FedRep, FedBABU, LG-FedAvg, and Ditto on CIFAR-100 and Tiny-ImageNet with ViT, ResNet-34, and VGG-11.

SourcearXiv Machine LearningAuthor: Kannanthodath Induchoodan Ajay Menon, Christian Prehofer, Yunfei Xu, Toru Hirano
FedSPC: Shared Parameter Correction for Personalized Federated Learning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.13748] FedSPC: Shared Parameter Correction for Personalized Federated Learning

[Submitted on 11 Jun 2026]

Title:FedSPC: Shared Parameter Correction for Personalized Federated Learning

View a PDF of the paper titled FedSPC: Shared Parameter Correction for Personalized Federated Learning, by Kannanthodath Induchoodan Ajay Menon and 3 other authors

View PDF HTML (experimental)

Abstract:Personalized federated learning (PFL) is one of the important approaches in federated learning for addressing statistical heterogeneity while enabling client-specific adaptation. Many PFL methods split the model into shared and personalized parameters, which are jointly trained on each client. However, this creates an optimization issue: shared parameters are updated by clients optimizing different local objectives, which can lead to inconsistent shared updates and weaken the shared representation. To address this problem, we propose Federated Shared Parameter Correction (FedSPC), a modular correction method for PFL. FedSPC applies control-variate correction only to the shared parameters of a given PFL method, while leaving personalized parameters unchanged. It can be integrated into three common PFL settings: shared feature extractors, shared classifiers, and fully shared models with local regularization. Experiments on CIFAR-100 and Tiny-ImageNet with ViT, ResNet-34, and VGG-11 show that FedSPC improves performance across representative PFL methods, including FedPer, FedRep, FedBABU, LG-FedAvg, and Ditto.

Comments: Accepted for presentation at FL@FM-IJCAI'26, in conjunction with IJCAI 2026. 9 pages

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2606.13748 [cs.LG]

(or arXiv:2606.13748v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.13748

arXiv-issued DOI via DataCite

Submission history

From: Ajay Menon Kannanthodath Induchoodan [view email] [v1] Thu, 11 Jun 2026 15:07:42 UTC (984 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled FedSPC: Shared Parameter Correction for Personalized Federated Learning, by Kannanthodath Induchoodan Ajay Menon and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • FedSPC corrects only shared parameters while leaving personalized parameters unchanged, making it modular and compatible with existing PFL methods.
  • The method supports three common PFL settings: shared feature extractors, shared classifiers, and fully shared models with local regularization.
  • Experiments show consistent performance gains across multiple datasets, architectures, and representative PFL baselines.

Highlights and analysis are generated automatically and may contain errors. Check the original source.