Explaining with Greater Support: Weighted Column Sampling Optimization for q-Consistent Summary-Explanations

TL;DR

This paper introduces a relaxed $q$-consistent summary-explanation approach that balances support and consistency, and proposes a weighted column sampling method to efficiently solve the complex max-support problem, improving scalability and explanation quality.

Contribution

It presents a novel $q$-consistent summary-explanation framework and a weighted column sampling technique to efficiently optimize support in explanations.

Findings

WCS method improves solution scalability and efficiency.

Solutions have greater support and better global extrapolation.

The approach balances support and consistency effectively.

Abstract

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.