CVPRApr, 2021

基于群集驱动的多域图联邦学习

TL;DRCluster-driven Graph Federated Learning (FedCG) proposes a novel method for learning a central model in privacy-constrained scenarios, overcoming statistical heterogeneity by identifying domains via FL-compliant clustering, instantiating domain-specific modules, connecting them through Graph Convolutional Networks (GCNs), and learning to cluster unsupervised via teacher-student classifier-training iterations to achieve state-of-the-art results on multiple Federated Learning benchmarks.