提出去中心化联邦学习架构，实现可信、可验证、激励对齐的边缘协同训练。
Trustless Federated Learning at Edge-Scale: A Compositional Architecture for Decentralized, Verifiable, and Incentive-Aligned Coordination
- 用密码学凭证证明聚合正确性，防止中间人篡改
- 通过几何新颖度检测避免参与方恶意刷贡献
- 支持并行所有权管理，提升系统扩展性，适合大规模设备协同
人工智能正从集中式模型训练转向分布式协作。当前，大量边缘设备持有敏感数据，但受限于缺乏可信聚合机制、激励设计漏洞、状态更新串行化导致扩展性差，以及治理存在事后篡改风险，协同建模愿景尚未实现。本文提出一种组合式架构：利用密码学凭证验证聚合结果的正确性；引入几何新颖度测量机制，防止激励博弈与虚假贡献；采用并行对象所有权设计，实现线性可扩展性；通过时间锁定策略防范事后操纵。该架构支持去中心化、可验证、激励对齐的边缘协同学习，为大规模隐私保护模型训练提供基础。
原文摘要 · Abstract (English)
Artificial intelligence is retracing the Internet's path from centralized provision to distributed creation. Initially, resource-intensive computation concentrates within institutions capable of training and serving large models.Eventually, as federated learning matures, billions of edge devices holding sensitive data will be able to collectively improve models without surrendering raw information, enabling both contribution and consumption at scale. This democratic vision remains unrealized due to certain compositional gaps; aggregators handle updates without accountability, economic mechanisms are lacking and even when present remain vulnerable to gaming, coordination serializes state modifications limiting scalability, and governance permits retroactive manipulation. This work addresses these gaps by leveraging cryptographic receipts to prove aggregation correctness, geometric novelty measurement to prevent incentive gaming, parallel object ownership to achieve linear scalability, and time-locked policies to check retroactive manipulation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。