Trang chủ / Tin tức / Khoa học & công nghệ
Khoa học & công nghệ

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

03/11/2026 · Thành viên: TS. Hồ Lệ Thi · Nguồn: OpenAlex

Customizing Pretrained Models (PMs) for downstream tasks demands task-specific data, which burgeoning Web3 applications provide abundantly. Blockchain-powered federated learning (BCFL) offers a sec...

<p><strong>Tác giả:</strong> Hong Lin, Zhongle Xie, Lidan Shou, Ke Chen, Gang Chen</p>

<p>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 const...</p>

<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3799682.3840574" target="_blank" rel="noopener">https://doi.org/10.1145/3799682.3840574</a></p>

<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3799682.3840574" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>

Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex