Explainable Machine Learning with Prior Knowledge: An Overview

05/21/2021
by   Katharina Beckh, et al.
0

This survey presents an overview of integrating prior knowledge into machine learning systems in order to improve explainability. The complexity of machine learning models has elicited research to make them more explainable. However, most explainability methods cannot provide insight beyond the given data, requiring additional information about the context. We propose to harness prior knowledge to improve upon the explanation capabilities of machine learning models. In this paper, we present a categorization of current research into three main categories which either integrate knowledge into the machine learning pipeline, into the explainability method or derive knowledge from explanations. To classify the papers, we build upon the existing taxonomy of informed machine learning and extend it from the perspective of explainability. We conclude with open challenges and research directions.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 10

05/06/2021

Explainable Autonomous Robots: A Survey and Perspective

Advanced communication protocols are critical to enable the coexistence ...
03/29/2019

Informed Machine Learning - Towards a Taxonomy of Explicit Integration of Knowledge into Machine Learning

Despite the great successes of machine learning, it can have its limits ...
12/11/2019

Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches

Explanations in Machine Learning come in many forms, but a consensus reg...
07/10/2020

Impact of Legal Requirements on Explainability in Machine Learning

The requirements on explainability imposed by European laws and their im...
07/10/2020

Machine Learning Explainability for External Stakeholders

As machine learning is increasingly deployed in high-stakes contexts aff...
05/13/2021

Explainable Machine Learning for Fraud Detection

The application of machine learning to support the processing of large d...
07/17/2020

Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context

Concerns about the societal impact of AI-based services and systems has ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.