BriefGPT.xyz
Apr, 2025
医学人工智能中的联邦学习、伦理学与双重黑箱问题
Federated learning, ethics, and the double black box problem in medical AI
HTML
PDF
Joshua Hatherley, Anders Søgaard, Angela Ballantyne, Ruben Pauwels
TL;DR
本研究针对医学领域联邦学习(FL)在伦理风险方面的不足研究展开,提出了“联邦不透明性”的新概念及其引发的双重黑箱问题,揭示了医疗FL可能被夸大的益处与面临的关键挑战。研究强调,确保FL在医疗伦理上的可行性,需克服这些挑战。
Abstract
Federated Learning
(FL) is a machine learning approach that allows multiple devices or institutions to collaboratively train a model without sharing their local data with a third-party. FL is considered a promising way to address patient
→