AI RESEARCH
Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning
arXiv CS.AI
•
ArXi:2605.18892v1 Announce Type: cross 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.