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

University of Oxford, Oxford Internet Institute, Students

Luciano Floridi

University of Oxford - Oxford Internet Institute

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)

University of Oxford, Oxford Internet Institute, Students ( email )

1 St. Giles
Oxford, Oxfordshire OX1 3JS
United Kingdom

Luciano Floridi

University of Oxford - Oxford Internet Institute ( email )

1 St. Giles
University of Oxford
Oxford OX1 3PG Oxfordshire, Oxfordshire OX1 3JS
United Kingdom

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
244
Abstract Views
878
rank
138,926
PlumX Metrics