Monotone Functions and Expert Models for Explanation of Machine Learning Models

There are significant difficulties for the acceptance of black-box Machine Learning (ML) models by subject matter experts (SMEs) despite significant achievements of many black-box models. A promising way to address this problem is by building a trustable, qualitative, interpretable models for the ta...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / International Conference on Information Visualisation pp. 1 - 9
Main Authors: Huber, Harlow, Kovalerchuk, Boris
Format: Conference Proceeding
Language:English
Published: IEEE 22.07.2024
Subjects:
Closed box
Data Mining
Diabetes
Interview
Interviews
Knowledge Discovery
Machine learning
Monotone Boolean Functions
Monotone Ordinal Functions
Monotonicity
Numerical models
Optimization
Ordinal Data
Subject Matter Expert (SME)
Subject matter experts
Training data
Visualization
ISSN:2375-0138
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:There are significant difficulties for the acceptance of black-box Machine Learning (ML) models by subject matter experts (SMEs) despite significant achievements of many black-box models. A promising way to address this problem is by building a trustable, qualitative, interpretable models for the task based on SME knowledge. Such qualitative models can work as qualitative explainers of black-box models or as sanity checks for them. In this paper, qualitative models operate with ordinal attributes, which can be Boolean or k-valued attributes with a small k . Humans easier understand and reason with such attributes that with continuous numeric attributes with many more values. Some ML tasks do not have sufficient training data. Building qualitative models with a SME ("expert models") is a way to solve these tasks solely with a SME's knowledge. The proposed Monotone Ordinal Expert Knowledge Acquisition (MOEKA) system allows building "expert models" through interview phases with the SME. Monotonicity is a key property of the system that is tested and used to shorten the interview process with a SME along with new methods for selecting the order of questions. MOEKA rather directly approximates domain knowledge in contrast with other ML explainers, which approximate black-box ML models. MOEKA can be also used as a method of database searching. Several case studies on gout, diabetes, and housing demonstrate efficiency of MOEKA.
ISSN:2375-0138
DOI:10.1109/IV64223.2024.00048