Federated Learning (FL) deals with learning a central model (i.e. the server)
in privacy-constrained scenarios, where data are stored on multiple devices
(i.e. the clients). The central model has no direct access to the data, but
only to the updates of the parameters computed locally by each client. This
raises a problem, known as statistical heterogeneity, because the clients may
have different data distributions (i.e. domains). This is only partly
alleviated by clustering the clients. Clustering may reduce heterogeneity by
identifying the domains, but it deprives each cluster model of the data and
supervision of others. Here we propose a novel Cluster-driven Graph Federated
Learning (FedCG). In FedCG, clustering serves to address statistical
heterogeneity, while Graph Convolutional Networks (GCNs) enable sharing
knowledge across them. FedCG: i) identifies the domains via an FL-compliant
clustering and instantiates domain-specific modules (residual branches) for
each domain; ii) connects the domain-specific modules through a GCN at training
to learn the interactions among domains and share knowledge; and iii) learns to
cluster unsupervised via teacher-student classifier-training iterations and to
address novel unseen test domains via their domain soft-assignment scores.
Thanks to the unique interplay of GCN over clusters, FedCG achieves the
state-of-the-art on multiple FL benchmarks.

Cluster-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.