EdgeServe:一种面向去中心化模型服务的流式系统
EdgeServe: A Streaming System for Decentralized Model Serving
AI总结:
本文提出分布式流式系统EdgeServe,用于解决数据流场景下机器学习模型服务中的数据路由、时间同步和速率控制问题,并在人类活动识别、自动驾驶和网络入侵检测三个任务上验证了其实时预测能力。
摘要:
机器学习任务的相关特征可能以一条或多条连续数据流的形式到达。在数据流上服务机器学习模型,在管理数据路由、时间同步和速率控制方面带来了许多有趣的系统挑战。本文提出了EdgeServe,一个能够实时提供机器学习模型预测的分布式流式系统。我们在三个流式预测任务上对EdgeServe进行了评估:(1)人类活动识别,(2)自动驾驶,以及(3)网络入侵检测。
英文摘要:
The relevant features for a machine learning task may arrive as one or more continuous streams of data. Serving machine learning models over streams of data creates a number of interesting systems challenges in managing data routing, time-synchronization, and rate control. This paper presents EdgeServe, a distributed streaming system that can serve predictions from machine learning models in real time. We evaluate EdgeServe on three streaming prediction tasks: (1) human activity recognition, (2) autonomous driving, and (3) network intrusion detection.
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。