An Efficient Framework for Monitoring Subgroup Performance of Machine Learning Systems

TL;DR

This paper introduces an efficient Bayesian optimization-based framework for monitoring and identifying the worst-performing data subgroups in machine learning systems post-deployment, reducing labeling costs.

Contribution

It formulates subgroup performance monitoring as an optimization problem and applies Bayesian optimization to efficiently find the worst-performing subgroup with limited labeled data.

Findings

Successfully identifies worst-performing subgroups in real-world datasets

Reduces labeling effort compared to exhaustive methods

Demonstrates effectiveness across multiple machine learning systems

Abstract

Monitoring machine learning systems post deployment is critical to ensure the reliability of the systems. Particularly importance is the problem of monitoring the performance of machine learning systems across all the data subgroups (subpopulations). In practice, this process could be prohibitively expensive as the number of data subgroups grows exponentially with the number of input features, and the process of labelling data to evaluate each subgroup's performance is costly. In this paper, we propose an efficient framework for monitoring subgroup performance of machine learning systems. Specifically, we aim to find the data subgroup with the worst performance using a limited number of labeled data. We mathematically formulate this problem as an optimization problem with an expensive black-box objective function, and then suggest to use Bayesian optimization to solve this problem. Our experimental results on various real-world datasets and machine learning systems show that our proposed framework can retrieve the worst-performing data subgroup effectively and efficiently.