Metraipolis › archive › dc_e1e36995b352

DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3 — arXiv:2610.39132

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39132
License (as archived)
CC0-1.0
Archived
2026-10-31T06:19:39.095Z
SHA-256 of the archived text
3442da9a62e33984caa29fd7fdee1487dad5693412ba9266ecbae8c3626692c4
Stable URL of this page
https://metraipolis.com/documento/dc_e1e36995b352

How to cite

DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3 — arXiv:2610.39132 — arXiv (en), https://arxiv.org/abs/2610.39132 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e1e36995b352 (Metraipolis archive dc_e1e36995b352, sha256 3442da9a62e33984caa29fd7fdee1487dad5693412ba9266ecbae8c3626692c4)
BibTeX
@misc{dce1e36995b352,
  title = {DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3 — arXiv:2610.39132},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39132},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e1e36995b352; sha256 3442da9a62e33984caa29fd7fdee1487dad5693412ba9266ecbae8c3626692c4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39132. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Customizing Pretrained Models (PMs) for downstream tasks demands task-specific data, which burgeoning Web3 applications provide abundantly. Blockchain-powered federated learning (BCFL) offers a secure and privacy-preserving paradigm to customize PMs among self-interested and untrusted Web3 participants. Yet, existing BCFL algorithms face severe efficiency and scalability challenges when applied to large PMs, due to their substantial computational and memory requirements and the hardware constraints of many participants. This paper introduces DICE, a novel BCFL algorithm that addresses the efficiency and scalability challenges of customizing large PMs in Web3 via two sets of synergistic techniques: (i) a dynamic progressive learning scheme and a model slice verification scheme to enable a wider range of honest participants, including those unable to deploy the full model, to engage in customizing PMs, while preserving model utility; (ii) a tree-structured committee consensus protocol and an efficiency-driven incentive scheme to address the dominant bottleneck that hinders existing BCFL algorithms from scaling to a larger number of data holders for customizing data-hungry large PMs, while maintaining security. Theoretical analysis and extensive experimental results on customizing vision and language PMs demonstrate DICE's efficiency, effectiveness, and security.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.39132 — 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 2026-10-31T06:07:53.395Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).