Explaining Any ML Model? – On Goals and Capabilities of XAI

06/28/2022
by   Moritz Renftle, et al.
0

An increasing ubiquity of machine learning (ML) motivates research on algorithms to explain ML models and their predictions – so-called eXplainable Artificial Intelligence (XAI). Despite many survey papers and discussions, the goals and capabilities of XAI algorithms are far from being well understood. We argue that this is because of a problematic reasoning scheme in XAI literature: XAI algorithms are said to complement ML models with desired properties, such as "interpretability", or "explainability". These properties are in turn assumed to contribute to a goal, like "trust" in an ML system. But most properties lack precise definitions and their relationship to such goals is far from obvious. The result is a reasoning scheme that obfuscates research results and leaves an important question unanswered: What can one expect from XAI algorithms? In this article, we clarify the goals and capabilities of XAI algorithms from a concrete perspective: that of their users. Explaining ML models is only necessary if users have questions about them. We show that users can ask diverse questions, but that only one of them can be answered by current XAI algorithms. Answering this core question can be trivial, difficult or even impossible, depending on the ML application. Based on these insights, we outline which capabilities policymakers, researchers and society can reasonably expect from XAI algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/12/2022

Explaining Predictions from Machine Learning Models: Algorithms, Users, and Pedagogy

Model explainability has become an important problem in machine learning...
research
08/24/2022

Augmented cross-selling through explainable AI – a case from energy retailing

The advance of Machine Learning (ML) has led to a strong interest in thi...
research
05/01/2020

The Grammar of Interactive Explanatory Model Analysis

When analysing a complex system, very often an answer for one question r...
research
01/20/2022

From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI

The rising popularity of explainable artificial intelligence (XAI) to un...
research
02/07/2020

What Would You Ask the Machine Learning Model? Identification of User Needs for Model Explanations Based on Human-Model Conversations

Recently we see a rising number of methods in the field of eXplainable A...
research
08/30/2022

The alignment problem from a deep learning perspective

Within the coming decades, artificial general intelligence (AGI) may sur...
research
05/27/2020

(Non)-neutrality of science and algorithms: Machine Learning between fundamental physics and society

The impact of Machine Learning (ML) algorithms in the age of big data an...

Please sign up or login with your details

Forgot password? Click here to reset