TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction Article Swipe

MAKE IMPACT

Weijie Liu , Ziwei Zhan , Carlee Joe‐Wong , Edith C.‐H. Ngai , Jingpu Duan , Deke Guo , Xu Chen , Xiaoxi Zhang · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2504.17528

Non-independent and identically distributed (Non-IID) data across edge clients have long posed significant challenges to federated learning (FL) training in edge computing environments. Prior works have proposed various methods to mitigate this statistical heterogeneity. While these works can achieve good theoretical performance, in this work we provide the first investigation into a hidden over-correction phenomenon brought by the uniform model correction coefficients across clients adopted by existing methods. Such over-correction could degrade model performance and even cause failures in model convergence. To address this, we propose TACO, a novel algorithm that addresses the non-IID nature of clients' data by implementing fine-grained, client-specific gradient correction and model aggregation, steering local models towards a more accurate global optimum. Moreover, we verify that leading FL algorithms generally have better model accuracy in terms of communication rounds rather than wall-clock time, resulting from their extra computation overhead imposed on clients. To enhance the training efficiency, TACO deploys a lightweight model correction and tailored aggregation approach that requires minimum computation overhead and no extra information beyond the synchronized model parameters. To validate TACO's effectiveness, we present the first FL convergence analysis that reveals the root cause of over-correction. Extensive experiments across various datasets confirm TACO's superior and stable performance in practice.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2504.17528

PDF

https://arxiv.org/pdf/2504.17528

OA Status

green

OpenAlex ID

https://openalex.org/W4415064098

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415064098

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2504.17528

Digital Object Identifier

Title

TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-04-24

Full publication date if available

Authors

Weijie Liu, Ziwei Zhan, Carlee Joe‐Wong, Edith C.‐H. Ngai, Jingpu Duan, Deke Guo, Xu Chen, Xiaoxi Zhang

List of authors in order

Landing page

https://arxiv.org/abs/2504.17528

Publisher landing page

PDF URL

https://arxiv.org/pdf/2504.17528

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2504.17528

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload