Federated clustering with GAN-based data synthesis

Federated clustering is an adaptation of centralized clustering in the federated settings, which aims to cluster data based on a global similarity measure while keeping all data local. The key here is how to construct a global similarity measure without sharing private data. To handle this, k-FED and federated fuzzy c-means (FFCM) respectively adapted K-means and fuzzy c-means to the federated learning settings, which aim to construct $K$ global cluster centroids by running K-means on a set of all local cluster centroids. However, the constructed global cluster centroids may be fragile and be sensitive to different non-independent and identically distributed (Non-IID) levels among clients. To handle this, we propose a simple but effective federated clustering framework with GAN-based data synthesis, which is called synthetic data aided federated clustering (SDA-FC). It outperforms k-FED and FFCM in terms of effectiveness and robustness, requires only one communication round, can run asynchronously, and can handle device failures. Moreover, although NMI is a far more commonly used metric than Kappa, empirical results indicate that Kappa is a more reliable one.