Suryanarayana, S.A., Sarne, D., Kraus, S. (2022). Explainability in Mechanism Design: Recent Advances and the Road Ahead. In: Baumeister, D., Rothe, J. (eds) Multi-Agent Systems. EUMAS 2022. Lecture Notes in Computer Science(), vol 13442. Springer, Cham. https://doi.org/10.1007/978-3-031-20614-6_21
Explainability in mechanism design : recent advances and the road ahead
|Author:||Suryanarayana, Sharadhi Alape1,2; Sarne, David1; Kraus, Sarit1|
1Department of Computer Science, Bar-Ilan University, Ramat Gan, Israel
2Centre for Ubiquitous Computing, University of Oulu, Oulu, Finland
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2023033033928
|Publish Date:|| 2023-12-11
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.
Lecture notes in computer science
|Pages:||364 - 382|
Multi-Agent Systems : 19th European Conference, EUMAS 2022, Düsseldorf, Germany, September 14–16, 2022, Proceedings
|Host publication editor:||
European Conference on Multi-Agent Systems
|Type of Publication:||
A4 Article in conference proceedings
|Field of Science:||
113 Computer and information sciences
This work was supported in part by the Data Science Institute at Bar-Ilan University, the EU Project TAILOR under grant 952215 and the Israeli Ministry of Science & Technology under grant 89583. The research was carried out with the technological support and funding from the HRI Consortium – the Israel Innovation Authority. Sharadhi Alape Suryanarayana is grateful for the President’s Scholarship and Erasmus+ Global Mobility Programme that has supported this research.
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG.