GraphGANFed: 面向高效药物发现的基于图结构分子的联邦生成框架（英文版）

英文标题：GraphGANFed: A Federated Generative Framework for Graph-Structured Molecules Towards Efficient Drug Discovery中文摘要：本文提出了一种 GraphGANFed 框架，该框架将图形卷积神经网络（GCN）、生成对抗网络（GAN）和联邦学习（FL）作为整体系统来生成新的分子，而不共享本地数据集，实现了数据隐私的保护，并且在三个基准数据集上进行了广泛的模拟，证明了 GraphGANFed 的可行性和有效性。英文摘要：Recent advances in deep learning have accelerated its use in variousapplications, such as cellular image analysis and molecular discovery. Inmolecular discovery, a generative adversarial network (GAN), which comprises adiscriminator t