DFedSat：面向低轨卫星星座的通信高效且鲁棒的去中心化联邦学习
DFedSat: Communication-Efficient and Robust Decentralized Federated Learning for LEO Satellite Constellations
AI总结：
本文提出面向低轨卫星星座的去中心化联邦学习框架DFedSat，通过轨道面内与跨轨道面自适应聚合及自补偿机制，在保证通信效率和鲁棒性的同时实现更快的收敛。
摘要：
低地球轨道（LEO）卫星在6G移动网络和空天地一体化系统的发展中发挥着关键作用。近年来空间技术的进步使LEO卫星具备了运行AI应用的能力。然而，以地面站（GS）为服务器、卫星为客户端的集中式方法，由于卫星与地面站之间的间歇性连接，往往收敛缓慢且效率低下。相比之下，去中心化联邦学习（DFL）通过星间链路（ISL）促进卫星（客户端）之间的直接通信，提供了一种有前景的替代方案。然而，由于多普勒频移和指向限制，连接不同轨道面卫星的跨轨道面ISL是动态变化的，这可能影响模型传播并导致收敛变慢。为缓解这些问题，我们提出了DFedSat，一个专为LEO卫星量身定制的完全去中心化联邦学习框架。DFedSat通过分别采用两种自适应机制进行轨道面内和跨轨道面模型聚合来加速训练过程。此外，还集成了自补偿机制以增强跨轨道面ISL对传输失败的鲁棒性。进一步地，我们推导了DFedSat在非凸情形下的次线性收敛速率。大量实验结果表明，DFedSat在收敛速度、通信效率和对不可靠链路的韧性方面优于其他DFL基线。
英文摘要：
Low Earth Orbit (LEO) satellites play a crucial role in the development of 6G mobile networks and space-air-ground integrated systems. Recent advancements in space technology have empowered LEO satellites with the capability to run AI applications. However, centralized approaches, where ground stations (GSs) act as servers and satellites as clients, often encounter slow convergence and inefficiencies due to intermittent connectivity between satellites and GSs. In contrast, decentralized federated learning (DFL) offers a promising alternative by facilitating direct communication between satellites (clients) via inter-satellite links (ISLs). However, inter-plane ISLs connecting satellites from different orbital planes are dynamic due to Doppler shifts and pointing limitations. This could impact model propagation and lead to slower convergence. To mitigate these issues, we propose DFedSat, a fully decentralized federated learning framework tailored for LEO satellites. DFedSat accelerates the training process by employing two adaptive mechanisms for intra-plane and inter-plane model aggregation, respectively. Furthermore, a self-compensation mechanism is integrated to enhance the robustness of inter-plane ISLs against transmission failure. Additionally, we derive the sublinear convergence rate for the non-convex case of DFedSat. Extensive experimental results demonstrate DFedSat's superiority over other DFL baselines regarding convergence rate, communication efficiency, and resilience to unreliable links.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
