Graph Theory Meets Federated Learning over Satellite Constellations: Spanning Aggregations, Network Formation, and Performance Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911298661384192 |
|---|---|
| author | Nadimi, Fardis Abdisarabshali, Payam Chakareski, Jacob Mastronarde, Nicholas Hosseinalipour, Seyyedali |
| author_facet | Nadimi, Fardis Abdisarabshali, Payam Chakareski, Jacob Mastronarde, Nicholas Hosseinalipour, Seyyedali |
| contents | In this work, we introduce Fed-Span: \textit{\underline{fed}erated learning with \underline{span}ning aggregation over low Earth orbit (LEO) satellite constellations}. Fed-Span aims to address critical challenges inherent to distributed learning in dynamic satellite networks, including intermittent satellite connectivity, heterogeneous computational capabilities of satellites, and time-varying satellites' datasets. At its core, Fed-Span leverages minimum spanning tree (MST) and minimum spanning forest (MSF) topologies to introduce spanning model aggregation and dispatching processes for distributed learning. To formalize Fed-Span, we offer a fresh perspective on MST/MSF topologies by formulating them through a set of continuous constraint representations (CCRs), thereby integrating these topologies into a distributed learning framework for satellite networks. Using these CCRs, we obtain the energy consumption and latency of operations in Fed-Span. Moreover, we derive novel convergence bounds for Fed-Span, accommodating its key system characteristics and degrees of freedom (i.e., tunable parameters). Finally, we propose a comprehensive optimization problem that jointly minimizes model prediction loss, energy consumption, and latency of {Fed-Span}. We unveil that this problem is NP-hard and develop a systematic approach to transform it into a geometric programming formulation, solved via successive convex optimization with performance guarantees. Through evaluations on real-world datasets, we demonstrate that Fed-Span outperforms existing methods, with faster model convergence, greater energy efficiency, and reduced latency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24932 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph Theory Meets Federated Learning over Satellite Constellations: Spanning Aggregations, Network Formation, and Performance Optimization Nadimi, Fardis Abdisarabshali, Payam Chakareski, Jacob Mastronarde, Nicholas Hosseinalipour, Seyyedali Distributed, Parallel, and Cluster Computing Machine Learning Networking and Internet Architecture In this work, we introduce Fed-Span: \textit{\underline{fed}erated learning with \underline{span}ning aggregation over low Earth orbit (LEO) satellite constellations}. Fed-Span aims to address critical challenges inherent to distributed learning in dynamic satellite networks, including intermittent satellite connectivity, heterogeneous computational capabilities of satellites, and time-varying satellites' datasets. At its core, Fed-Span leverages minimum spanning tree (MST) and minimum spanning forest (MSF) topologies to introduce spanning model aggregation and dispatching processes for distributed learning. To formalize Fed-Span, we offer a fresh perspective on MST/MSF topologies by formulating them through a set of continuous constraint representations (CCRs), thereby integrating these topologies into a distributed learning framework for satellite networks. Using these CCRs, we obtain the energy consumption and latency of operations in Fed-Span. Moreover, we derive novel convergence bounds for Fed-Span, accommodating its key system characteristics and degrees of freedom (i.e., tunable parameters). Finally, we propose a comprehensive optimization problem that jointly minimizes model prediction loss, energy consumption, and latency of {Fed-Span}. We unveil that this problem is NP-hard and develop a systematic approach to transform it into a geometric programming formulation, solved via successive convex optimization with performance guarantees. Through evaluations on real-world datasets, we demonstrate that Fed-Span outperforms existing methods, with faster model convergence, greater energy efficiency, and reduced latency. |
| title | Graph Theory Meets Federated Learning over Satellite Constellations: Spanning Aggregations, Network Formation, and Performance Optimization |
| topic | Distributed, Parallel, and Cluster Computing Machine Learning Networking and Internet Architecture |
| url | https://arxiv.org/abs/2509.24932 |