{"ID":2863710,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24932","arxiv_id":"2509.24932","title":"Graph Theory Meets Federated Learning over Satellite Constellations: Spanning Aggregations, Network Formation, and Performance Optimization","abstract":"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.","short_abstract":"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 connectivi...","url_abs":"https://arxiv.org/abs/2509.24932","url_pdf":"https://arxiv.org/pdf/2509.24932v3","authors":"[\"Fardis Nadimi\",\"Payam Abdisarabshali\",\"Jacob Chakareski\",\"Nicholas Mastronarde\",\"Seyyedali Hosseinalipour\"]","published":"2025-09-29T15:35:37Z","proceeding":"cs.DC","tasks":"[\"cs.DC\",\"cs.LG\",\"cs.NI\"]","methods":"[]","has_code":false}