paper-with-me

홈 › Papers

FedDPC : Handling Data Heterogeneity and Partial Client Participation in Federated Learning

2025-12-23 · Mrinmay Sen, Subhrajit Nag arxiv

Data heterogeneity is a significant challenge in modern federated learning (FL) as it creates variance in local model updates, causing the aggregated global model to shift away from the true global optimum. Partial client participation in FL further exacerbates this issue by skewing the aggregation of local models towards the data distribution of participating clients. This creates additional variance in the global model updates, causing the global model to converge away from the optima of the global objective. These variances lead to instability in FL training, which degrades global model performance and slows down FL training. While existing literature primarily focuses on addressing data heterogeneity, the impact of partial client participation has received less attention. In this paper, we propose FedDPC, a novel FL method, designed to improve FL training and global model performance by mitigating both data heterogeneity and partial client participation. FedDPC addresses these issues by projecting each local update onto the previous global update, thereby controlling variance in both local and global updates. To further accelerate FL training, FedDPC employs adaptive scaling for each local update before aggregation. Extensive experiments on image classification tasks with multiple heterogeneously partitioned datasets validate the effectiveness of FedDPC. The results demonstrate that FedDPC outperforms state-of-the-art FL algorithms by achieving faster reduction in training loss and improved test accuracy across communication rounds.

📄 PDF Abstract BibTeX arXiv:2512.20329

Code (0)

등록된 구현이 없습니다.

Tasks

Image ClassificationFederated Learning

Similar Papers 제목 키워드 기반

Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning

2023-09-21 · NeurIPS 2023 11

Federated learning (FL) is an effective machine learning paradigm where multiple clients can train models based on heterogeneous data in a decentralized manner without accessing their private data. However, existing FL s…

Anchor Sampling for Federated Learning with Partial Client Participation

2022-06-13 · Feijie Wu, Song Guo, Zhihao Qu, Shiqi He 외

Compared with full client participation, partial client participation is a more practical scenario in federated learning, but it may amplify some challenges in federated learning, such as data heterogeneity. The lack of …

Federated Learning

Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity

2021-05-02 · Saeed Vahidian, Mahdi Morafah, Bill Lin

The traditional approach in FL tries to learn a single global model collaboratively with the help of many clients under the orchestration of a central server. However, learning a single global model might not work well f…

Federated LearningPersonalized Federated Learning

An Aggregation-Free Federated Learning for Tackling Data Heterogeneity

2024-04-29 · CVPR 2024 1 · YuAn Wang, Huazhu Fu, Renuga Kanagavelu, Qingsong Wei 외

The performance of Federated Learning (FL) hinges on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models b…

Federated Learning

Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity

2023-05-29 · Konstantin Mishchenko, Rustem Islamov, Eduard Gorbunov, Samuel Horváth

We present a partially personalized formulation of Federated Learning (FL) that strikes a balance between the flexibility of personalization and cooperativeness of global training. In our framework, we split the variable…

Federated LearningPersonalized Federated Learning