The Missing Piece in Complex Analytics: Low Latency, Scalable Model Management and Serving with Velox
Daniel Crankshaw Peter Bailis Joseph E. Gonzalez Haoyuan Li Zhao Zhang Michael J. Franklin Ali Ghodsi Michael I. Jordan UC Berkeley AMPLab
Abstract
To enable complex data-intensive applications such as personalized recommendations, targeted advertising, and intelligent services, the data management community has focused heavily on the design of systems to train complex models on large datasets. Unfortunately, the design of these systems largely ignores a critical component of the overall analytics process: the serving and management of models at scale. In this work, we present Velox, a new component of the Berkeley Data Analytics Stack. Velox is a data management system for facilitating the next steps in real-world, large-scale analytics pipelines: online model management, maintenance, and serving. Velox provides end-user applications and services with a low-latency, intuitive interface to models, transforming the raw statistical models currently trained using existing offline large-scale compute frameworks into full-blown, end-to-end data products capable of targeting advertisements, recommending products, and personalizing web content. To provide up-to-date results for these complex models, Velox also facilitates lightweight online model maintenance and selection (i.e., dynamic weighting). In this paper, we describe the chal
中文速览
大规模机器学习系统长期只重视模型训练，却忽视了一个关键环节——训练好的模型如何被高效地部署、查询和持续更新。为此，作者设计了 Velox，一个专门负责机器学习模型在线服务与管理（online model serving and management）的系统，作为伯克利数据分析栈（BDAS）的新组件。Velox 通过智能缓存与分布式内存计算实现毫秒级预测响应，同时结合离线批量重训练与在线增量更新，让模型随新数据持续保持新鲜；它还引入探索-利用（bandit）机制来处理推荐系统中的反馈闭环问题，并提供模型版本管理与性能监控，使模型退化时能自动触发再训练或快速回滚。这项工作填补了从原始统计模型到可交付的真实数据产品之间长期缺失的工程环节，为工业界普遍存在的"各自为政、手工拼凑"的模型上线方式提供了一个系统化的替代方案。
原文 arXiv:1409.3809;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1409.3809v2