Logic Constraints to Feature Importances

TL;DR

This paper introduces a method to incorporate human prior knowledge of feature importance into AI models through regularization, enhancing interpretability and trustworthiness, with promising results in fairness applications.

Contribution

It proposes a novel framework that extends empirical loss with a regularization term based on feature importance constraints, leveraging local interpretability methods.

Findings

Effective in improving fairness on the Adult dataset

Framework is model-agnostic and adaptable to various applications

Enhances interpretability and trustworthiness of AI models

Abstract

In recent years, Artificial Intelligence (AI) algorithms have been proven to outperform traditional statistical methods in terms of predictivity, especially when a large amount of data was available. Nevertheless, the "black box" nature of AI models is often a limit for a reliable application in high-stakes fields like diagnostic techniques, autonomous guide, etc. Recent works have shown that an adequate level of interpretability could enforce the more general concept of model trustworthiness. The basic idea of this paper is to exploit the human prior knowledge of the features' importance for a specific task, in order to coherently aid the phase of the model's fitting. This sort of "weighted" AI is obtained by extending the empirical loss with a regularization term encouraging the importance of the features to follow predetermined constraints. This procedure relies on local methods for the feature importance computation, e.g. LRP, LIME, etc. that are the link between the model weights to be optimized and the user-defined constraints on feature importance. In the fairness area, promising experimental results have been obtained for the Adult dataset. Many other possible applications of this model agnostic theoretical framework are described.