SOFA-FL: Self-Organizing Hierarchical Federated Learning with Adaptive Clustered Data Sharing
Yi Ni, Xinkun Wang, Han Zhang
TL;DR
Addresses data heterogeneity and evolving environments in federated learning by proposing SOFA-FL, a self-organizing hierarchical framework built on DMAC for initialization, SHAPE for topology evolution, and Adaptive Clustered Data Sharing to mitigate heterogeneity. The framework is evaluated on MNIST with non-IID data, showing superior accuracy and fairness compared to HypCluster. Results demonstrate that dynamic topology adaptation and controlled data sharing enhance personalization and robustness in hierarchical FL without fixed cluster structures.
Abstract
Federated Learning (FL) faces significant challenges in evolving environments, particularly regarding data heterogeneity and the rigidity of fixed network topologies. To address these issues, this paper proposes \textbf{SOFA-FL} (Self-Organizing Hierarchical Federated Learning with Adaptive Clustered Data Sharing), a novel framework that enables hierarchical federated systems to self-organize and adapt over time. The framework is built upon three core mechanisms: (1) \textbf{Dynamic Multi-branch Agglomerative Clustering (DMAC)}, which constructs an initial efficient hierarchical structure; (2) \textbf{Self-organizing Hierarchical Adaptive Propagation and Evolution (SHAPE)}, which allows the system to dynamically restructure its topology through atomic operations -- grafting, pruning, consolidation, and purification -- to adapt to changes in data distribution; and (3) \textbf{Adaptive Clustered Data Sharing}, which mitigates data heterogeneity by enabling controlled partial data exchange between clients and cluster nodes. By integrating these mechanisms, SOFA-FL effectively captures dynamic relationships among clients and enhances personalization capabilities without relying on predetermined cluster structures.