为卫星星座设计高效联邦学习框架，显著缩短训练时间。
Space for Improvement: Navigating the Design Space for Federated Learning in Satellite Constellations
- 提出适配太空环境的联邦学习算法改造方法
- 在自研平台FLySTacK上实现算法验证，性能优于现有方案
- 开发自治型联邦学习系统，适合大规模卫星集群部署
空间正成为机器学习的新应用领域，多颗卫星已具备机载深度学习能力。为应对下行链路带宽不足问题，需在轨预处理数据，而通过联邦学习（FL）实现整个星座协同训练是可行路径。尽管现有研究已针对特定场景调整了联邦学习算法，但理论实现仍存在诸多限制，阻碍实际部署。为此，本文从多方面开展系统性探索：1）提出对现有联邦学习算法的太空适配方法；2）构建新型卫星星座仿真与硬件感知测试平台FLySTacK，进行严格算法评估；3）提出通用、分层、自治的AutoFLSat联邦学习算法，在多个场景下相较领先方案实现12.5%至37.5%的模型训练时间降低。
原文摘要 · Abstract (English)
Space has emerged as an exciting new application area for machine learning, with several missions equipping deep learning capabilities on-board spacecraft. Pre-processing satellite data through on-board training is necessary to address the satellite downlink deficit, as not enough transmission opportunities are available to match the high rates of data generation. To scale this effort across entire constellations, collaborated training in orbit has been enabled through federated learning (FL). While current explorations of FL in this context have successfully adapted FL algorithms for scenario-specific constraints, these theoretical FL implementations face several limitations that prevent progress towards real-world deployment. To address this gap, we provide a holistic exploration of the FL in space domain on several fronts. 1) We develop a method for space-ification of existing FL algorithms, evaluated on 2) FLySTacK, our novel satellite constellation design and hardware aware testing platform where we perform rigorous algorithm evaluations. Finally we introduce 3) AutoFLSat, a generalized, hierarchical, autonomous FL algorithm for space that provides a 12.5% to 37.5% reduction in model training time than leading alternatives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。