arxiv3d agobullish

FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels

arXiv:2604.20825v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training without sharing raw data; however, the presence of noisy labels across distributed clients can severely degrade the learning performance. In this paper, we propose FedSIR, a multi-stage frame

FE1 model #federated-learning #noisy-labels #robust-training Read on arxiv →

arxiv5d agobullish

Mixture of Predefined Experts: Maximizing Data Usage on Vertical Federated Learning

arXiv:2602.12708v2 Announce Type: replace Abstract: Vertical Federated Learning (VFL) has emerged as a critical paradigm for collaborative model training in privacy-sensitive domains such as finance and healthcare. However, most existing VFL frameworks rely on the idealized assumption of full sample

SPLAVE5 models · +2 #federated-learning #collaborative-model-training #privacy-sensitive-domains Read on arxiv →

arxivApr 10bullish

Adaptive Differential Privacy for Federated Medical Image Segmentation Across Diverse Modalities

arXiv:2604.06518v1 Announce Type: cross Abstract: Large volumes of medical data remain underutilized because centralizing distributed data is often infeasible due to strict privacy regulations and institutional constraints. In addition, models trained in centralized settings frequently fail to gener

#medical-imaging #federated-learning #privacy Read on arxiv →