Explaining with Greater Support: Weighted Column Sampling Optimization for q-Consistent Summary-Explanations
This work addresses the need for more scalable and effective explanations in critical domains like healthcare and criminal justice, though it is incremental as it builds on existing summary-explanation frameworks.
The paper tackles the problem of generating globally-consistent summary-explanations for machine learning decisions, which often have small support, by proposing a relaxed q-consistent version to achieve greater support with slightly lower consistency, and introduces a weighted column sampling method that improves solution time efficiency and yields solutions with greater support and better global extrapolation effectiveness.
Machine learning systems have been extensively used as auxiliary tools in domains that require critical decision-making, such as healthcare and criminal justice. The explainability of decisions is crucial for users to develop trust on these systems. In recent years, the globally-consistent rule-based summary-explanation and its max-support (MS) problem have been proposed, which can provide explanations for particular decisions along with useful statistics of the dataset. However, globally-consistent summary-explanations with limited complexity typically have small supports, if there are any. In this paper, we propose a relaxed version of summary-explanation, i.e., the $q$-consistent summary-explanation, which aims to achieve greater support at the cost of slightly lower consistency. The challenge is that the max-support problem of $q$-consistent summary-explanation (MSqC) is much more complex than the original MS problem, resulting in over-extended solution time using standard branch-and-bound solvers. To improve the solution time efficiency, this paper proposes the weighted column sampling~(WCS) method based on solving smaller problems by sampling variables according to their simplified increase support (SIS) values. Experiments verify that solving MSqC with the proposed SIS-based WCS method is not only more scalable in efficiency, but also yields solutions with greater support and better global extrapolation effectiveness.