梳理MLOps关键挑战，给出通用落地建议
Machine Learning Operations: A Mapping Study
- 通过系统性映射分析MLOps各环节痛点
- 识别数据、建模、部署三大管道核心问题
- 提供跨场景可复用的工具与解决方案
机器学习与人工智能近年来被众多企业采纳。机器学习运维（MLOps）借鉴持续软件工程流程（如DevOps），用于将机器学习模型部署至生产环境。然而，由于涉及诸多复杂因素，许多机器学习项目无法成功进入生产阶段。本文探讨MLOps流水线中数据处理、模型构建和部署环节存在的问题，通过系统性映射研究识别出不同关注领域的挑战，并基于此提出切实可行的工具或解决方案建议。本研究的核心价值在于系统性地梳理了MLOps中的关键挑战，并提供了对应的推荐方案。这些建议不依赖特定工具，适用于科研与工业双重场景。
原文摘要 · Abstract (English)
Machine learning and AI have been recently embraced by many companies. Machine Learning Operations, (MLOps), refers to the use of continuous software engineering processes, such as DevOps, in the deployment of machine learning models to production. Nevertheless, not all machine learning initiatives successfully transition to the production stage owing to the multitude of intricate factors involved. This article discusses the issues that exist in several components of the MLOps pipeline, namely the data manipulation pipeline, model building pipeline, and deployment pipeline. A systematic mapping study is performed to identify the challenges that arise in the MLOps system categorized by different focus areas. Using this data, realistic and applicable recommendations are offered for tools or solutions that can be used for their implementation. The main value of this work is it maps distinctive challenges in MLOps along with the recommended solutions outlined in our study. These guidelines are not specific to any particular tool and are applicable to both research and industrial settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。