Feb, 2022
面向可追溯和可复现的联邦学习:一种事实表方法
Towards an Accountable and Reproducible Federated Learning: A FactSheets
Approach
TL;DRAF^2 Framework introduces accountability to Federated Learning by fusing verifiable claims with tamper-evident facts, into reproducible arguments, enabling validation, reproduction, and certification of Federated Learning processes to address AI engineering and ethics challenges.