English(EN) Asynchronous Federated Continual Segmentation with Evolving Clients and Label Spaces

新框架支持具有演进式客户端的灵活联邦学习

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-10 04:00

研究人员开发了一个名为 CA-MMDS 的新框架，以应对联邦学习中的挑战，特别是针对演进式客户端集和变化的标签空间。这种持续多模型蒸馏方法允许异步客户端参与，并通过维护客户端模型的服务器端存档来降低通信成本。全局模型不是通过完全模型聚合来更新，而是通过从存档的本地模型进行蒸馏来更新，使其在现实世界的动态联邦中更加灵活和高效。该框架在多类 3D 腹部 CT 分割任务中表现出具有竞争力的性能。 AI

影响该框架可以提高动态、现实世界环境中协作式 AI 模型训练的效率和灵活性。

排序理由该集群包含一篇详细介绍联邦学习新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍联邦学习新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 101 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Can Peng, Qianhui Men, Pramit Saha, Qianye Yang, Yingyu Yang, Shuwei Xing, Cheng Ouyang, J. Alison Noble · 2026-07-10 04:00

具有不断变化的客户端和标签空间的异步联邦持续分割

arXiv:2503.15414v3 Announce Type: replace-cross Abstract: Federated learning seeks to foster collaboration among distributed clients while preserving the privacy of their local data. Traditional federated learning methods typically assume a fixed setting, where participating clie…

本文如何被排名

报道来源 [1]

具有不断变化的客户端和标签空间的异步联邦持续分割

相关实体

相关话题