Metraipolis › archive › dc_5edd9e12a504

Iapetus: Content-Aware Hierarchical Scheduling for Collaborative ViT Inference in LEO Satellite Networks — arXiv:2609.03318

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03318
License (as archived)
CC0-1.0
Archived
2026-10-17T01:47:28.000Z
SHA-256 of the archived text
8cb756faf8c47fda874b12ea02dbca4be6b96ffbd5af35ad5dcce6f155017802
Stable URL of this page
https://metraipolis.com/documento/dc_5edd9e12a504

How to cite

Iapetus: Content-Aware Hierarchical Scheduling for Collaborative ViT Inference in LEO Satellite Networks — arXiv:2609.03318 — arXiv (en), https://arxiv.org/abs/2609.03318 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5edd9e12a504 (Metraipolis archive dc_5edd9e12a504, sha256 8cb756faf8c47fda874b12ea02dbca4be6b96ffbd5af35ad5dcce6f155017802)
BibTeX
@misc{dc5edd9e12a504,
  title = {Iapetus: Content-Aware Hierarchical Scheduling for Collaborative ViT Inference in LEO Satellite Networks — arXiv:2609.03318},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03318},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5edd9e12a504; sha256 8cb756faf8c47fda874b12ea02dbca4be6b96ffbd5af35ad5dcce6f155017802},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03318. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Collaborative inference pools distributed resources to run compute-intensive Vision Transformers (ViTs) in satellite edge computing. Model partitioning enables such collaboration by assigning consecutive layer groups to different nodes, but the large volume of intermediate activation data incurs substantial transfer overhead that can erase its benefit. Token compression reduces downstream computation and activation transfer, but its quality impact depends on input content, model depth, and earlier pruning decisions, while layer offloading must adapt to time-varying contact and battery conditions. We present \sys, a content-aware hierarchical scheduler that screens constellation-wide options to retain a bounded candidate set, then refines each candidate into a complete token compression and layer offloading trajectory using quality prediction and joint planning. A unified objective balances per-task latency, energy, and quality loss against accumulated workload and battery pressures. We implement \sys on an NVIDIA Jetson AGX Orin hardware-in-the-loop testbed and use its validated execution model for constellation-scale trace replay across multiple ViT workloads and constellation settings. At \(5\)~tasks/s, \sys accomplishes 91.6\% of released tasks, 26.1 percentage points above MARATD3, the strongest baseline, while reducing mean latency and battery draw by 53.0\% and 70.8\%, respectively, and meeting quality targets.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-04 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.03318 — 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 2026-10-17T01:12:01.333Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).