论文标题
Tinymlops：广泛边缘AI采用的运营挑战
TinyMLOps: Operational Challenges for Widespread Edge AI Adoption
论文作者
论文摘要
在边缘设备上部署机器学习应用程序可以带来明显的好处，例如改善的可靠性，延迟和隐私，但也引入了自己的挑战。大多数工作都集中在边缘平台的有限计算资源上，但这并不是唯一站在广泛采用的瓶颈。在本文中，我们列出了Tinyml从业人员在Edge设备上操作应用程序时可能需要考虑的其他一些挑战。我们专注于监视和管理应用程序，MLOPS平台的共同功能等任务，并展示它们如何与边缘部署的分布式性质变得复杂。我们还讨论了边缘应用程序所独有的问题，例如保护模型的知识产权和验证其完整性。
Deploying machine learning applications on edge devices can bring clear benefits such as improved reliability, latency and privacy but it also introduces its own set of challenges. Most works focus on the limited computational resources of edge platforms but this is not the only bottleneck standing in the way of widespread adoption. In this paper we list several other challenges that a TinyML practitioner might need to consider when operationalizing an application on edge devices. We focus on tasks such as monitoring and managing the application, common functionality for a MLOps platform, and show how they are complicated by the distributed nature of edge deployment. We also discuss issues that are unique to edge applications such as protecting a model's intellectual property and verifying its integrity.
