DFCA: Decentralized Federated Clustering Algorithm
This addresses the problem of applying clustered federated learning to realistic decentralized networks for practitioners, though it is incremental as it builds on existing clustered FL approaches.
The paper tackles the problem of clustered federated learning's reliance on a central server, which creates bottlenecks and single points of failure, by introducing DFCA, a fully decentralized algorithm that enables clients to train cluster-specific models without central coordination. Experiments show DFCA outperforms other decentralized algorithms and performs comparably to centralized IFCA, even under sparse connectivity.
Clustered Federated Learning has emerged as an effective approach for handling heterogeneous data across clients by partitioning them into clusters with similar or identical data distributions. However, most existing methods, including the Iterative Federated Clustering Algorithm (IFCA), rely on a central server to coordinate model updates, which creates a bottleneck and a single point of failure, limiting their applicability in more realistic decentralized learning settings. In this work, we introduce DFCA, a fully decentralized clustered FL algorithm that enables clients to collaboratively train cluster-specific models without central coordination. DFCA uses a sequential running average to aggregate models from neighbors as updates arrive, providing a communication-efficient alternative to batch aggregation while maintaining clustering performance. Our experiments on various datasets demonstrate that DFCA outperforms other decentralized algorithms and performs comparably to centralized IFCA, even under sparse connectivity, highlighting its robustness and practicality for dynamic real-world decentralized networks.