The relevant features for a machine learning task may be aggregated from data sources collected on different nodes in a network. This problem, which we call decentralized prediction, creates a number of interesting systems challenges in managing data routing, placing computation, and time-synchronization. This paper presents EdgeServe, a machine learning system that can serve decentralized predictions. EdgeServe relies on a low-latency message broker to route data through a network to nodes that can serve predictions. EdgeServe relies on a series of novel optimizations that can tradeoff computation, communication, and accuracy. We evaluate EdgeServe on three decentralized prediction tasks: (1) multi-camera object tracking, (2) network intrusion detection, and (3) human activity recognition.

翻译：一项机器学习任务的相关特征可能通过聚合网络中不同节点上收集的数据源获取。我们称此问题为去中心化预测，其在数据路由、计算部署与时序同步方面引发了一系列有趣的系统挑战。本文提出EdgeServe，一个能够服务去中心化预测的机器学习系统。EdgeServe依赖低延迟消息代理将数据路由至网络中可执行预测的节点，并采用一系列创新优化方法以折中计算、通信与精度之间的权衡。我们在三个去中心化预测任务上评估了EdgeServe：（1）多摄像头目标跟踪，（2）网络入侵检测，（3）人类活动识别。