# FedSPC: Shared Parameter Correction for Personalized Federated Learning

Source: [FedSPC: Shared Parameter Correction for Personalized Federated Learning](<https://www.sota2.com/research/paper/6a2f870ed33dfb23e783bf4b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-16T05:00:05.515Z

Authors: Kannanthodath Induchoodan Ajay Menon, Christian Prehofer, Yunfei Xu, Toru Hirano

Published: 2026-06-11T15:07:42.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-100 (FedSPC Evaluation)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-fedspc-evaluation.md>): Image Classification; CIFAR-100; Base Top-1 Accuracy: not recorded.

- [Image Classification on Tiny-ImageNet (Base Top-1 Acc, FedSPC Top-1 Acc, Delta)](<https://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-base-top-1-acc-fedspc-top-1-acc-delta.md>): Image Classification; Tiny-ImageNet; Base Top-1 Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.13748>)

[PDF](<https://arxiv.org/pdf/2606.13748.pdf>)