English(EN) MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks

MANE框架提升多设备边缘AI推理能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了MANE，一个新颖的分布式推理框架，旨在提高深度神经网络边缘卸载的效率。该系统通过采用多路径尾部架构，在运行时动态调整精度-吞吐量权衡，解决了边缘服务器支持多个并发设备的挑战。MANE在为多达40个设备满足延迟服务水平目标（SLOs）方面表现出80%的成功率，优于现有方法，并保持比设备端替代方案更高的准确性。 AI

影响提高了边缘AI推理的效率，使更多设备能够在不影响性能的情况下利用共享服务器资源。

排序理由该集群包含一篇详细介绍深度神经网络推理新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 15 / 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深度神经网络推理新框架的研究论文。[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: infra, paper; 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.AI TIER_1 English(EN) · Sokratis Nikolaidis, Stylianos I. Venieris, Leonidas Malachias, Iakovos S. Venieris · 2026-09-15 04:00

MANE：用于深度神经网络边缘卸载的多路径自适应网络

arXiv:2609.14660v1 Announce Type: cross Abstract: Split computing constitutes a widely used distributed inference approach, where a lightweight head model is onloaded onto the device and a heavier tail model resides on an edge server, leveraging the growing computational capabili…

本文如何被排名

报道来源 [1]

MANE：用于深度神经网络边缘卸载的多路径自适应网络

相关实体

相关话题