Explainability in Mechanism Design: Recent Advances and the Road Ahead.

Sharadhi Alape Suryanarayana; David Sarne; Sarit Kraus

doi:10.48550/ARXIV.2206.03031

Explainability in Mechanism Design: Recent Advances and the Road Ahead.

Sharadhi Alape Suryanarayana
, David Sarne
, Sarit Kraus

Research output: Other contribution

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.

Original language	English
Publisher	Cornell University Library, arXiv.org
Volume	abs/2206.03031
DOIs	https://doi.org/10.48550/ARXIV.2206.03031
State	Published - 2022

Bibliographical note

DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

Access to Document

10.48550/ARXIV.2206.03031License: Unspecified

https://dblp.org/rec/journals/corr/abs-2206-03031

Cite this

@misc{b46c22b671514f7d8fd2563ed654e9d2,

title = "Explainability in Mechanism Design: Recent Advances and the Road Ahead.",

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. ",

author = "Suryanarayana, \{Sharadhi Alape\} and David Sarne and Sarit Kraus",

note = "DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",

year = "2022",

doi = "10.48550/ARXIV.2206.03031",

language = "אנגלית",

volume = "abs/2206.03031",

publisher = "Cornell University Library, arXiv.org",

type = "Other",

}

TY - GEN

T1 - Explainability in Mechanism Design: Recent Advances and the Road Ahead.

AU - Suryanarayana, Sharadhi Alape

AU - Sarne, David

AU - Kraus, Sarit

N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

U2 - 10.48550/ARXIV.2206.03031

DO - 10.48550/ARXIV.2206.03031

M3 - ???researchoutput.researchoutputtypes.othercontribution.other???

VL - abs/2206.03031

PB - Cornell University Library, arXiv.org

ER -

Explainability in Mechanism Design: Recent Advances and the Road Ahead.

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this