论文标题
异步：具有高海拔平台的Leo卫星星座的异步联合学习
AsyncFLEO: Asynchronous Federated Learning for LEO Satellite Constellations with High-Altitude Platforms
论文作者
论文摘要
低地球轨道（LEO）星座，每个星座都包含大量卫星，已成为“从天空中”的大数据的新来源。将此类数据下载到地面站（GS）以进行大数据分析需要很高的带宽，并且涉及大型传播延迟。联合学习（FL）提供了一个有希望的解决方案，因为它允许数据保持原位（永不离开卫星），并且仅需要传输机器学习模型参数（对卫星数据进行了培训）。但是，由于由Straggler卫星引起的瓶颈，在卫星通信（SATCOM）的背景下，在卫星通信（SATCOM）的背景下训练单个FL模型可能需要几天的时间才能训练单个FL模型。在本文中，我们为LEO星座提出了一个称为Asyncfleo的异步FL框架，以提高SATCOM的FL效率。 Asynfleo不仅解决了同步FL的瓶颈（闲置等待），而且还解决了由Straggler卫星引起的模型陈旧问题。 ASYNCFLEO利用将“在天空中”作为参数服务器定位的高海拔平台（HAP），由三个技术组件组成：（1）一种模型传播算法的明星通信拓扑结构，（2）模型聚合算法与卫星组合和结构量的模型聚集算法。我们对IID和非IID数据的广泛评估表明，Asyncfleo的表现优于最高水平的状态，从而将收敛延迟减少了22倍，并将准确性提高了40％。
Low Earth Orbit (LEO) constellations, each comprising a large number of satellites, have become a new source of big data "from the sky". Downloading such data to a ground station (GS) for big data analytics demands very high bandwidth and involves large propagation delays. Federated Learning (FL) offers a promising solution because it allows data to stay in-situ (never leaving satellites) and it only needs to transmit machine learning model parameters (trained on the satellites' data). However, the conventional, synchronous FL process can take several days to train a single FL model in the context of satellite communication (Satcom), due to a bottleneck caused by straggler satellites. In this paper, we propose an asynchronous FL framework for LEO constellations called AsyncFLEO to improve FL efficiency in Satcom. Not only does AsynFLEO address the bottleneck (idle waiting) in synchronous FL, but it also solves the issue of model staleness caused by straggler satellites. AsyncFLEO utilizes high-altitude platforms (HAPs) positioned "in the sky" as parameter servers, and consists of three technical components: (1) a ring-of-stars communication topology, (2) a model propagation algorithm, and (3) a model aggregation algorithm with satellite grouping and staleness discounting. Our extensive evaluation with both IID and non-IID data shows that AsyncFLEO outperforms the state of the art by a large margin, cutting down convergence delay by 22 times and increasing accuracy by 40%.
