Metraipolis › archive › dc_af4749322fa9

MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks — arXiv:2609.14660

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14660
License (as archived)
CC0-1.0
Archived
2026-10-15T22:53:16.512Z
SHA-256 of the archived text
cfbc16547a55bf120ecfed74e054853bea7f3713e9e360e20bfe94b41c69de7a
Stable URL of this page
https://metraipolis.com/documento/dc_af4749322fa9

How to cite

MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks — arXiv:2609.14660 — arXiv (en), https://arxiv.org/abs/2609.14660 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af4749322fa9 (Metraipolis archive dc_af4749322fa9, sha256 cfbc16547a55bf120ecfed74e054853bea7f3713e9e360e20bfe94b41c69de7a)
BibTeX
@misc{dcaf4749322fa9,
  title = {MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks — arXiv:2609.14660},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14660},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af4749322fa9; sha256 cfbc16547a55bf120ecfed74e054853bea7f3713e9e360e20bfe94b41c69de7a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14660. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 capabilities of modern System-on-Chips while alleviating server load. As intelligent indoor environments such as smart offices grow increasingly populated with diverse IoT devices, a single edge server must simultaneously assist multiple devices, each competing for the same shared inference resources. Without a principled mechanism to manage this shared load, the server is quickly overwhelmed, causing latency SLO violations and rendering server-assisted inference ineffective. In this work, we present MANE, a distributed inference framework that equips the server with a multi-path tail architecture, enabling a dynamic accuracy--throughput trade-off at runtime. By introducing a novel multi-path model architecture, a three-stage training scheme featuring a Joint Head Network Distillation loss and a hysteresis-based scheduler with an equitable device-fallback policy, MANE maintains over 80% SLO satisfaction rate where state-of-the-art onloading methods fail completely, while preserving accuracy 6pp higher than on-device alternatives, across up to 40 concurrent devices.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.14660 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:29:03.708Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).