Explainability in Mechanism Design: Recent Advances and the Road Ahead

TL;DR

This paper surveys recent progress in explainability within mechanism design, highlighting its unique challenges and proposing future directions for making social choice mechanisms more transparent and understandable.

Contribution

It provides a comprehensive overview of explainability in mechanism design, distinguishing it from general AI explainability and discussing specific challenges and solutions.

Findings

Identify key properties and goals of explainability in mechanism design

Highlight challenges unique to social choice explainability

Propose potential solution concepts for explainability issues

Abstract

Designing and implementing explainable systems is seen as the next step towards increasing user trust in, acceptance of and reliance on Artificial Intelligence (AI) systems. While explaining choices made by black-box algorithms such as machine learning and deep learning has occupied most of the limelight, systems that attempt to explain decisions (even simple ones) in the context of social choice are steadily catching up. In this paper, we provide a comprehensive survey of explainability in mechanism design, a domain characterized by economically motivated agents and often having no single choice that maximizes all individual utility functions. We discuss the main properties and goals of explainability in mechanism design, distinguishing them from those of Explainable AI in general. This discussion is followed by a thorough review of the challenges one may face when working on Explainable Mechanism Design and propose a few solution concepts to those.