Fiper: a Visual-based Explanation Combining Rules and Feature Importance

TL;DR

Fiper introduces a visual explanation method that combines rules and feature importance to improve interpretability of AI models, validated through a user study comparing it with traditional outputs.

Contribution

The paper presents a novel visual-based explanation technique integrating rules and feature importance, emphasizing a user-centered approach in Explainable AI.

Findings

Visual explanations improved user understanding over textual outputs.

Participants found the visual method more intuitive and easier to interpret.

The approach enhances transparency of black-box models in high-stakes domains.

Abstract

Artificial Intelligence algorithms have now become pervasive in multiple high-stakes domains. However, their internal logic can be obscure to humans. Explainable Artificial Intelligence aims to design tools and techniques to illustrate the predictions of the so-called black-box algorithms. The Human-Computer Interaction community has long stressed the need for a more user-centered approach to Explainable AI. This approach can benefit from research in user interface, user experience, and visual analytics. This paper proposes a visual-based method to illustrate rules paired with feature importance. A user study with 15 participants was conducted comparing our visual method with the original output of the algorithm and textual representation to test its effectiveness with users.