用于监控和改进ML模型的模型断言
Model Assertions for Monitoring and Improving ML Models
摘要：
机器学习模型越来越多地部署在具有真实世界交互的环境中，例如车辆，但不幸的是，这些模型可能会以系统的方式失败。为了防止错误，ML工程团队监控并不断改进这些模型。我们提出了一个新的抽象，模型断言，它适应了程序断言的经典使用，作为监控和改进ML模型的一种方式。模型断言是对模型的输入和输出的任意函数，其指示何时可能发生错误，例如，如果视频中的对象迅速改变其类别，则触发该功能。我们提出了在ML系统部署的所有阶段使用模型断言的方法，包括运行时监控，验证标签和不断改进ML模型。对于运行时监控，我们表明，模型断言可以找到高置信度的错误，其中模型返回错误的输出具有高置信度，基于不确定性的监控技术不会检测到。对于训练，我们提出了两种使用模型断言的方法。首先，我们提出了一个基于bandit的主动学习算法，该算法可以从断言标记的数据中进行采样，并表明它可以比传统的基于不确定性的方法减少高达40%的标记成本。其次，我们提出了一个用于生成“一致性断言”的API（例如，类变化的例子）和弱标签的输入一致性断言失败，并表明这些弱标签可以提高高达46%的相对模型质量。我们使用视频、激光雷达和心电图数据评估了四个真实任务的模型断言。
英文摘要：
ML models are increasingly deployed in settings with real world interactions such as vehicles, but unfortunately, these models can fail in systematic ways. To prevent errors, ML engineering teams monitor and continuously improve these models. We propose a new abstraction, model assertions, that adapts the classical use of program assertions as a way to monitor and improve ML models. Model assertions are arbitrary functions over a model's input and output that indicate when errors may be occurring, e.g., a function that triggers if an object rapidly changes its class in a video. We propose methods of using model assertions at all stages of ML system deployment, including runtime monitoring, validating labels, and continuously improving ML models. For runtime monitoring, we show that model assertions can find high confidence errors, where a model returns the wrong output with high confidence, which uncertainty-based monitoring techniques would not detect. For training, we propose two methods of using model assertions. First, we propose a bandit-based active learning algorithm that can sample from data flagged by assertions and show that it can reduce labeling costs by up to 40% over traditional uncertainty-based methods. Second, we propose an API for generating "consistency assertions" (e.g., the class change example) and weak labels for inputs where the consistency assertions fail, and show that these weak labels can improve relative model quality by up to 46%. We evaluate model assertions on four real-world tasks with video, LIDAR, and ECG data.
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。
