Learning Recourse Costs from Pairwise Feature Comparisons

TL;DR

This paper introduces a method to infer feature modification costs for recourse in machine learning models using pairwise human comparisons and the Bradley-Terry model, reducing the need for exhaustive surveys.

Contribution

It proposes a novel approach to learn feature-wise costs from non-exhaustive human comparison surveys using the Bradley-Terry model, enabling more practical recourse generation.

Findings

Efficiently learns feature costs from partial human comparisons.

Non-exhaustive surveys suffice to infer complete feature costs.

Demonstrates practical application in recourse algorithms.

Abstract

This paper presents a novel technique for incorporating user input when learning and inferring user preferences. When trying to provide users of black-box machine learning models with actionable recourse, we often wish to incorporate their personal preferences about the ease of modifying each individual feature. These recourse finding algorithms usually require an exhaustive set of tuples associating each feature to its cost of modification. Since it is hard to obtain such costs by directly surveying humans, in this paper, we propose the use of the Bradley-Terry model to automatically infer feature-wise costs using non-exhaustive human comparison surveys. We propose that users only provide inputs comparing entire recourses, with all candidate feature modifications, determining which recourses are easier to implement relative to others, without explicit quantification of their costs. We demonstrate the efficient learning of individual feature costs using MAP estimates, and show that these non-exhaustive human surveys, which do not necessarily contain data for each feature pair comparison, are sufficient to learn an exhaustive set of feature costs, where each feature is associated with a modification cost.