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

arXiv: https://arxiv.org/abs/2512.08267 · HTML: https://mlsanity.com/paper/2512.08267/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 4 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Builds on (most cited first, 1 of 1)

- [Hierarchical Federated Learning with Multi-Timescale Gradient Correction](https://mlsanity.com/paper/2409.18448/) (2024)

## Abstract (arXiv)

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 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) Dynamic Multi-branch Agglomerative Clustering (DMAC), which constructs an initial efficient hierarchical structure; (2) 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) 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.