Interpretable Artificial Intelligence through the Lens of Feature Interaction

TL;DR

This paper emphasizes the importance of feature interactions in interpreting deep learning models and surveys methods that explicitly consider these interactions to improve trustworthiness and fairness.

Contribution

It highlights the significance of feature interactions in model interpretability and reviews modern methods that explicitly incorporate these interactions.

Findings

Feature interactions are crucial for understanding deep learning models.

Many interpretability methods overlook feature interactions.

Considering feature interactions enhances model transparency.

Abstract

Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations. Despite this, many view interpretability as a key solution to trustworthiness, fairness, and safety, especially as deep learning is applied to more critical decision tasks like credit approval, job screening, and recidivism prediction. There is an abundance of good research providing interpretability to deep learning models; however, many of the commonly used methods do not consider a phenomenon called "feature interaction." This work first explains the historical and modern importance of feature interactions and then surveys the modern interpretability methods which do explicitly consider feature interactions. This survey aims to bring to light the importance of feature interactions in the larger context of machine learning interpretability, especially in a modern context where deep learning models heavily rely on feature interactions.