研究人员正在开发新的联邦学习 (FL) 策略来应对数据异质性和安全威胁等挑战。FedImp 和 FedTVD 旨在通过根据数据质量和分布对客户端贡献进行加权来提高收敛速度和模型准确性。FedSGA 专注于优化异构环境中的模型拆分，而 STAR-FL 则引入了针对计算机视觉 FL 系统中数据投毒攻击的防御措施。这些进展共同提高了联邦学习的效率、鲁棒性和安全性。 AI
影响 联邦学习的这些进展可能导致在分布式数据上训练出更高效、更安全、更个性化的 AI 模型。
排序理由 arXiv 上发表了多篇研究论文，详细介绍了联邦学习的新算法和策略。
AI 生成摘要 · Google Gemini · 来自 7 个来源。 我们如何撰写摘要 →
arXiv:2608.18634v1 Announce Type: new Abstract: Federated Active Learning (FAL) addresses the dual challenges of data privacy and label scarcity, where the absence of a global data view introduces additional hurdles for coordinated query selection. We study cross-silo FAL in the …
arXiv:2608.17849v1 Announce Type: new Abstract: Split federated learning (SFL) has emerged as a powerful paradigm for model training at the edge. However, SFL inherently involves discrete decision variables for model splitting and resource allocation, resulting in a challenging m…
arXiv:2608.15639v1 Announce Type: cross Abstract: \textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients. However, under client heterogeneity, the conventional static split strategy may be suboptimal because…
arXiv:2608.14861v1 Announce Type: cross Abstract: Data poisoning attacks pose serious security threats to Federated Learning (FL) systems in Computer Vision. Despite growing research attention, two key challenges remain for existing defense techniques: (1) accurately distinguishi…
arXiv:2608.15107v1 Announce Type: new Abstract: Federated learning (FL) is a practical framework that can train models on distributed user data while guaranteeing data privacy; however, due to heterogeneity in which each user has a different data distribution, problems frequently…
arXiv:2608.14654v1 Announce Type: cross Abstract: Federated Learning (FL) is a collaborative paradigm that enables multiple devices to train a global model while preserving local data privacy. A major challenge in FL is the non-Independent and Identically Distributed (non-IID) na…
Federated Learning (FL) enables collaborative model training across distributed client devices while preserving data privacy. However, FL faces significant challenges due to data heterogeneity, particularly in terms of label distribution skewness and variations in dataset sizes, …