English(EN) FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices

FANS框架优化异构联邦学习中的模型架构

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了FANS（Federated Adaptive Network Search，联邦自适应网络搜索）框架，旨在优化异构联邦学习环境中的模型架构。该方法利用超网络学习共享架构空间，超越了预定义的模型菜单。为了提高效率，引入了联邦并行缩放（FPS）算法，支持具有自蒸馏功能的多个子网络的并行训练。在CIFAR-10、CIFAR-100和MNLI数据集上的评估表明，与现有方法相比，FANS显著扩展了可行子网络的范围，并改善了准确性-效率权衡。 AI

影响增强了联邦学习的效率和架构灵活性，有可能在多样化设备上实现更复杂的模型。

排序理由详细介绍联邦学习新框架和算法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍联邦学习新框架和算法的学术论文。[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, model release, 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Jiaxin Zhang, Xingwei Wang, Bo Yi, Liang Zhao, Alireza Furutanpey, Ziyi Chen, Qiang He, Keqin Li, Schahram Dustdar · 2026-09-10 04:00

FANS：面向异构设备的联邦自适应网络搜索学习

arXiv:2609.06106v1 Announce Type: new Abstract: Heterogeneous Federated Learning (HFL) aims to train models across devices with diverse resource budgets while preserving data privacy. Existing HFL methods typically bind training to a small predefined menu of model configurations,…

本文如何被排名

报道来源 [1]

FANS：面向异构设备的联邦自适应网络搜索学习

相关实体

相关话题