SOFA-FL: Self-Organizing Hierarchical Federated Learning with Adaptive Clustered Data Sharing

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 $\mathbf{\text{SOFA-FL}}$ (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) $\mathbf{\text{Dynamic}}\mathbf{\text{Multi-branch}}\mathbf{\text{Agglomerative}}\mathbf{\text{Clustering}}\mathbf{\text{(DMAC)}}$, which constructs an initial efficient hierarchical structure; (2) $\mathbf{\text{Self-organizing}}\mathbf{\text{Hierarchical}}\mathbf{\text{Adaptive}}\mathbf{\text{Propagation}}\mathbf{\text{and}}\mathbf{\text{Evolution}}\mathbf{\text{(SHAPE)}}$, 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) $\mathbf{\text{Adaptive}}\mathbf{\text{Clustered}}\mathbf{\text{Data}}\mathbf{\text{Sharing}}$, 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.