The Explanation Game: A Formal Framework for Interpretable Machine Learning

35 Pages Posted: 17 Jan 2020 Last revised: 8 Apr 2020

See all articles by David Watson

David Watson

King's College London

Luciano Floridi

Yale University - Digital Ethics Center; University of Bologna- Department of Legal Studies

Date Written: December 26, 2019

Abstract

We propose a formal framework for interpretable machine learning. Combining elements from statistical learning, causal interventionism, and decision theory, we design an idealized explanation game in which players collaborate to find the best explanation(s) for a given algorithmic prediction. Through an iterative procedure of questions and answers, the players establish a three-dimensional Pareto frontier that describes the optimal trade-offs between explanatory accuracy, simplicity, and relevance. Multiple rounds are played at different levels of abstraction, allowing the players to explore overlapping causal patterns of variable granularity and scope. We characterize the conditions under which such a game is almost surely guaranteed to converge on a (conditionally) optimal explanation surface in polynomial time, and highlight obstacles that will tend to prevent the players from advancing beyond certain explanatory thresholds. The game serves a descriptive and a normative function, establishing a conceptual space in which to analyse and compare existing proposals, as well as design new and improved solutions.

Keywords: Algorithmic Explainability, Explanation Game, Interpretable Machine Learning, Pareto Frontier, Relevance

Suggested Citation

Watson, David and Floridi, Luciano, The Explanation Game: A Formal Framework for Interpretable Machine Learning (December 26, 2019). Available at SSRN: https://ssrn.com/abstract=3509737 or http://dx.doi.org/10.2139/ssrn.3509737

David Watson (Contact Author)

King's College London ( email )

Strand
London, England WC2R 2LS
United Kingdom

Luciano Floridi

Yale University - Digital Ethics Center ( email )

85 Trumbull Street
New Haven, CT CT 06511
United States
2034326473 (Phone)

University of Bologna- Department of Legal Studies ( email )

Via Zamboni 22
Bologna, Bo 40100
Italy

HOME PAGE: http://www.unibo.it/sitoweb/luciano.floridi/en

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
469
Abstract Views
2,353
Rank
114,868
PlumX Metrics