Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy
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 LearningExploiting Features and Logits in Heterogeneous Federated Learning
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 LearningManagementFair Federated Medical Image Segmentation via Client Contribution Estimation
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+1FedCCEA : A Practical Approach of Client Contribution Evaluation for Federated Learning
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 LearningSCALA: Split Federated Learning with Concatenated Activations and Logit Adjustments
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