Explainable Artificial Intelligence Approaches: A Survey

TL;DR

This survey reviews various Explainable AI methods, demonstrating their advantages and challenges through a credit default prediction case study, and discusses future directions for responsible, human-centered AI adoption.

Contribution

It provides a comprehensive comparison of XAI methods, analyzes their strengths and weaknesses, and offers insights and future research directions for responsible AI.

Findings

XAI methods vary in local and global explanations

Quantifying explainability remains challenging

Guidelines for responsible AI development

Abstract

The lack of explainability of a decision from an Artificial Intelligence (AI) based "black box" system/model, despite its superiority in many real-world applications, is a key stumbling block for adopting AI in many high stakes applications of different domain or industry. While many popular Explainable Artificial Intelligence (XAI) methods or approaches are available to facilitate a human-friendly explanation of the decision, each has its own merits and demerits, with a plethora of open challenges. We demonstrate popular XAI methods with a mutual case study/task (i.e., credit default prediction), analyze for competitive advantages from multiple perspectives (e.g., local, global), provide meaningful insight on quantifying explainability, and recommend paths towards responsible or human-centered AI using XAI as a medium. Practitioners can use this work as a catalog to understand, compare, and correlate competitive advantages of popular XAI methods. In addition, this survey elicits future research directions towards responsible or human-centric AI systems, which is crucial to adopt AI in high stakes applications.