Active Bayesian Assessment for Black-Box Classifiers
Skip to main content
Open Access Publications from the University of California

Active Bayesian Assessment for Black-Box Classifiers

  • Author(s): Ji, Disi
  • IV, Robert L Logan
  • Smyth, Padhraic
  • Steyvers, Mark
  • et al.
Creative Commons 'BY' version 4.0 license

Recent advances in machine learning have led to increased deployment of black-box classifiers across a wide variety of applications. In many such situations there is a crucial need to assess the performance of these pre-trained models, for instance to ensure sufficient predictive accuracy, or that class probabilities are well-calibrated. Furthermore, since labeled data may be scarce or costly to collect, it is desirable for such assessment be performed in an efficient manner. In this paper, we introduce a Bayesian approach for model assessment that satisfies these desiderata. We develop inference strategies to quantify uncertainty for common assessment metrics (accuracy, misclassification cost, expected calibration error), and propose a framework for active assessment using this uncertainty to guide efficient selection of instances for labeling. We illustrate the benefits of our approach in experiments assessing the performance of modern neural classifiers (e.g., ResNet and BERT) on several standard image and text classification datasets.

Many UC-authored scholarly publications are freely available on this site because of the UC's open access policies. Let us know how this access is important for you.

Main Content
Current View