paper-with-me

Papers

Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning

2026-05-17 · Asim Ukaye, Nurbek Tastan, Mubarak Abdu-Aguye, Karthik Nandakumar arxiv

Federated learning (FL) enables collaborative learning of computer vision models, where privacy and regulatory constraints prevent centralizing data across devices or organizations. However, practical FL deployments often exhibit severe class imbalance and label skew, causing standard aggregation protocols to overfit dominant clients and degrade minority-class performance. We propose a data-free, class-wise contribution estimation and aggregation framework based on logit maximization (CELM) that does not require sharing raw data, client metadata, or auxiliary public datasets. The FL server probes client updates to obtain class-wise evidence scores and assembles a cross-client evidence matrix, which quantifies both per-class competence and class coverage. Using this matrix, we compute contribution weights that upweight clients providing strong, discriminative evidence for underrepresented classes. The resulting aggregation is stable due to simplex constraints and momentum smoothing, and it remains compatible with standard FL training pipelines. We evaluate the approach on representative vision benchmarks under controlled non-IID and pathological label splits, demonstrating that CELM-based aggregation improves robustness to imbalance and statistical heterogeneity, while yielding better performance without requiring any additional data exchange.

📄 PDF Abstract BibTeX arXiv:2605.18892

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy

2026-04-24 · Asim Ukaye, Mubarak Abdu-Aguye, Nurbek Tastan, Karthik Nandakumar arxiv

Client contribution estimation in Federated Learning is necessary for identifying clients' importance and for providing fair rewards. Current methods often rely on server-side validation data or self-reported client info…

Federated Learning

Exploiting Features and Logits in Heterogeneous Federated Learning

2022-10-27 · Yun-Hin Chan, Edith C. -H. Ngai

Due to the rapid growth of IoT and artificial intelligence, deploying neural networks on IoT devices is becoming increasingly crucial for edge intelligence. Federated learning (FL) facilitates the management of edge devi…

Federated LearningManagement

Fair Federated Medical Image Segmentation via Client Contribution Estimation

2023-03-29 · CVPR 2023 1 · Meirui Jiang, Holger R Roth, Wenqi Li, Dong Yang 외

How to ensure fairness is an important topic in federated learning (FL). Recent studies have investigated how to reward clients based on their contribution (collaboration fairness), and how to achieve uniformity of perfo…

FairnessFederated LearningImage SegmentationMedical Image Segmentation+1

FedCCEA : A Practical Approach of Client Contribution Evaluation for Federated Learning

2021-06-04 · Sung Kuk Shyn, DongHee Kim, Kwangsu Kim

Client contribution evaluation, also known as data valuation, is a crucial approach in federated learning(FL) for client selection and incentive allocation. However, due to restrictions of accessibility of raw data, only…

Data ValuationFederated Learning

SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustments

2024-05-08 · Jiarong Yang, YuAn Liu

Split Federated Learning (SFL) is a distributed machine learning framework which strategically divides the learning process between a server and clients and collaboratively trains a shared model by aggregating local mode…

Federated Learning