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

Source: [SOFA-FL: Self-Organizing Hierarchical Federated Learning with Adaptive Clustered Data Sharing](<https://www.sota2.com/research/paper/6938febc6cfd488761a53ee0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-11T05:03:10.792Z

Authors: Yi Ni, Xinkun Wang, Han Zhang

Published: 2025-12-09T05:47:44.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on MNIST (test) (Federated Learning Fairness and Client Variance)](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-federated-learning-fairness-and-client-variance.md>): Image Classification; MNIST (test); Mean Accuracy: 98.18.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.08267>)

[PDF](<https://arxiv.org/pdf/2512.08267.pdf>)
