A Game-theoretic Understanding of Repeated Explanations in ML Models

02/05/2022
by   Kavita Kumari, et al.
3

This paper formally models the strategic repeated interactions between a system, comprising of a machine learning (ML) model and associated explanation method, and an end-user who is seeking a prediction/label and its explanation for a query/input, by means of game theory. In this game, a malicious end-user must strategically decide when to stop querying and attempt to compromise the system, while the system must strategically decide how much information (in the form of noisy explanations) it should share with the end-user and when to stop sharing, all without knowing the type (honest/malicious) of the end-user. This paper formally models this trade-off using a continuous-time stochastic Signaling game framework and characterizes the Markov perfect equilibrium state within such a framework.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/14/2023

One Explanation Does Not Fit XIL

Current machine learning models produce outstanding results in many area...
research
03/01/2020

An Information-Theoretic Approach to Explainable Machine Learning

A key obstacle to the successful deployment of machine learning (ML) met...
research
10/27/2022

Feature Necessity Relevancy in ML Classifier Explanations

Given a machine learning (ML) model and a prediction, explanations can b...
research
06/09/2021

A general approach for Explanations in terms of Middle Level Features

Nowadays, it is growing interest to make Machine Learning (ML) systems m...
research
09/08/2021

Model Explanations via the Axiomatic Causal Lens

Explaining the decisions of black-box models has been a central theme in...
research
06/10/2020

OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms

Local Interpretable Model-Agnostic Explanations (LIME) is a popular meth...
research
02/15/2022

On Deciding Feature Membership in Explanations of SDD Related Classifiers

When reasoning about explanations of Machine Learning (ML) classifiers, ...

Please sign up or login with your details

Forgot password? Click here to reset