Metraipolis › archive › dc_5dd03babf030

Cost-Aware Mixture-of-Experts Coordination for Model Markets — arXiv:2610.11908

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11908
License (as archived)
CC0-1.0
Archived
2026-10-09T06:24:15.842Z
SHA-256 of the archived text
db5163c011253d910b4b49c2151a92526cedc6ded41bbb31114ff31aa8330d6f
Stable URL of this page
https://metraipolis.com/documento/dc_5dd03babf030

How to cite

Cost-Aware Mixture-of-Experts Coordination for Model Markets — arXiv:2610.11908 — arXiv (en), https://arxiv.org/abs/2610.11908 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5dd03babf030 (Metraipolis archive dc_5dd03babf030, sha256 db5163c011253d910b4b49c2151a92526cedc6ded41bbb31114ff31aa8330d6f)
BibTeX
@misc{dc5dd03babf030,
  title = {Cost-Aware Mixture-of-Experts Coordination for Model Markets — arXiv:2610.11908},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11908},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5dd03babf030; sha256 db5163c011253d910b4b49c2151a92526cedc6ded41bbb31114ff31aa8330d6f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11908. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing model marketplaces typically trade and select individual models as indivisible units, limiting their ability to exploit complementarities among heterogeneous experts. This paper proposes an MoE-based model market framework that lifts Mixture-of-Experts from a model-level learning architecture to a market-level coordination mechanism. In this framework, brokers use gating networks to coordinate multiple heterogeneous experts and deliver a composite model service. We formalize the market participants, service workflow, expert cost structure, and a welfare objective that combines predictive utility with heterogeneous execution costs. We then derive a cost-aware gating mechanism and market-aware training objective, and introduce a cost-adjusted revenue allocation rule that distributes residual revenue according to realized expert participation and execution cost. We also establish basic theoretical properties of the allocation rule, including budget balance, participation monotonicity, and cost sensitivity. Experiments over five random seeds on fifteen tabular and image benchmarks use independently trained and frozen neural and tree-based experts together with latency-derived execution costs. MoE Market achieves the highest mean welfare on all fifteen datasets and a lower mean expected cost than Standard MoE in every case, while maintaining competitive predictive performance. The allocation experiments further demonstrate systematic sensitivity to expert participation and cost, together with substantially lower computational overhead than exact Shapley allocation. These results suggest that MoE can serve as a market-level coordination principle for collaborative, cost-aware, and economically grounded model marketplaces.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Databases (cs.DB) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.11908 — 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 2026-10-09T05:50:32.190Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).