The paper proposes an online learning framework for configuring dynamic constellation topologies in satellite networks, addressing the challenges posed by continuous orbital movement and node maneuvering. It does not rely on predefined orbital plane structures, making it robust to changes caused by satellite maneuvers. Experiments show that the method performs comparably to state‑of‑the‑art offline techniques and can be adapted to constrained online learning, balancing per‑iteration computational cost against convergence speed.
By Jo\~ao Norberto, Ricardo Ferreira, Cl\'audia Soares
The article proposes a comprehensive two‑dimensional system architecture for 6G LEO satellite Internet of Things, integrating LEO satellites with terrestrial networks. It evaluates three key enabling technologies: massive grant‑free random access for uplink, deep learning‑based multibeam precoding for downlink, and distributed cooperative routing for inter‑satellite links. An on‑orbit verification platform is introduced to validate the real‑world feasibility and performance of these solutions, and the paper concludes with open challenges and future research directions.
By Ming Ying, Xiaoming Chen, Qiao Qi, Yichao Xu, Jiajun Pan
Satellite mega-constellations are emerging as large-scale sensing, communication, and computation fabrics, yet their learning architectures remain largely inherited from terrestrial federated learning...
The paper introduces a heterogeneous federated learning approach using the FractalNet architecture tailored for satellite mega‑constellations. It formalizes contact‑window‑constrained, depth‑heterogeneous optimization and proposes a distributed path scheduler that assigns model depth based on satellite SWAP‑C constraints, predicted contacts, and training statistics. The framework includes periodic update pooling and a three‑tier agentic control plane, and is validated through a wildfire detection case study across LEO, MEO, and GEO/HEO shells, demonstrating improvements in convergence, communication efficiency, energy adaptation, and robustness.
By Sai Puppala, Koushik Sinha
arXiv:2608. 09687v1 Announce Type: new Abstract: Federated learning (FL) in Low Earth Orbit (LEO) satellite constellations is affected by non-IID data and irregular ground-station visibility, both driven by orbital geometry.
By Satwat Bashir, Tasos Dagiuklas, Muddesar Iqbal
arXiv:2608. 09208v1 Announce Type: cross Abstract: Decentralized intelligence systems with heterogeneous devices and limited coordination increasingly rely on decentralized federated learning (DFL).
By Van Truong Vo, Khoa Nguyen, Taehong Kim
Decentralized intelligence systems with heterogeneous devices and limited coordination increasingly rely on decentralized federated learning (DFL). However, DFL suffers from convergence inefficiency under data heterogeneity due to the use of a uniform learning rate (LR) that ignores layer-specific optimization needs.
arXiv:2606. 10774v2 Announce Type: replace Abstract: Decentralized Federated Learning(DFL) enables collaborative model training across wireless edge nodes, including IoT deployments, autonomous vehicles, UAV swarms, and satellite constellations.
By Chanuka A. S. Hewa Kaluannakkage, Rajkumar Buyya
STR-Agent is an LLM-driven framework designed for QoS-aware routing in Low Earth Orbit satellite networks. It integrates intent perception, tool-based execution, experience accumulation, and reflection-based policy adaptation to translate natural-language service requests into adaptive routing decisions. In simulations on a Walker-Delta constellation, STR-Agent reduces end-to-end delay by up to 60% compared with DQ-Dijkstra and improves intent-understanding accuracy from 45.4% to 92.45% after fine-tuning, with the Reflection Module providing additional delay reductions.
By Bowen Lu, Mugen Peng, Yaohua Sun, Hongyu Wang, Kerui Guo, Wenjia Xu
FedSAP is a federated learning framework that addresses heterogeneous edge devices by using structured pruning as a budget-constrained tri-state channel allocation. It partitions model channels into a Global pool, pseudo-domain-specific Private pools, and a Dropped state, allowing broadly useful features to be shared while isolating domain-sensitive updates. Experiments on Digits and Office-Caltech datasets show FedSAP achieving higher mean global accuracy than the strongest baseline while supporting up to 80% client pruning ratios.
By Wentao Yue, Tianyou Lai, Hongji Li, Qingyu Mao, Qilei Li
arXiv:2605.19892v2 Announce Type: replace-cross
Abstract: Dramatic cost reductions driven by private sector innovations have led to a rapid increase in the number of satellites in orbit and a corresp...
By Jonas Weiss, Patricia Sagmeister, Gabriel Maiolini Capez, Dinesh Verma, Roberto Garello, Alberto Perotti, Dawid Lazaj, Alicja Musial, Jakub Nalepa, Thomas Morf, Martin Schmatz, Marek Krawczyk, Mateusz Przeliorz, Kevin Roche, Sagar Tayal, Mahalakshmi Lakshminarayanan, Nicolas Long\'ep\'e, Pierre-Philippe Mathieu, Agata Wijata
Satellite-based distributed learning promises to train machine-learning models directly in orbit using massive, globally dispersed sensor data, thereby avoiding large-scale data downloads to ground se...