ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms

Huong Ha, Sunil Gupta, Santu Rana, Svetha Venkatesh

Keywords: active learning, bayesian learning, machine learning testing, information theory

Abstract: Machine learning models are being used extensively in many important areas, but there is no guarantee that a model will always perform well or as its developers intended. Understanding the correctness of a model is crucial to prevent potential failures that may have significant detrimental impact in critical application areas. In this paper, we propose a novel framework to efficiently test a machine learning model using only a small amount of labelled test data. The core idea is to efficiently estimate the metrics of interest for a model-under-test using Bayesian neural network. We develop a methodology to efficiently train the Bayesian neural network from the limited number of labelled data. We also devise an entropy-based sampling strategy to sample the data point such that the proposed framework can give accurate estimations for the metrics of interest. Finally, we conduct an extensive set of experiments to test various machine learning models for different types of metrics. Our experiments with multiple datasets show that given a testing budget, the estimation of the metrics by our method is significantly better compared to existing state-of-the-art approaches.

One-sentence Summary: We propose a novel framework for active testing of machine learning models.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=AVZo9a04Cw