EdgeServe: A Streaming System for Decentralized Model Serving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shaowang, Ted, Krishnan, Sanjay
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929253480660992
author Shaowang, Ted
Krishnan, Sanjay
author_facet Shaowang, Ted
Krishnan, Sanjay
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2303_08028
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle EdgeServe: A Streaming System for Decentralized Model Serving
Shaowang, Ted
Krishnan, Sanjay
Databases
Distributed, Parallel, and Cluster Computing
Machine Learning
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.
title EdgeServe: A Streaming System for Decentralized Model Serving
topic Databases
Distributed, Parallel, and Cluster Computing
Machine Learning
url https://arxiv.org/abs/2303.08028