Human Understandable Explanation Extraction for Black-box Classification Models Based on Matrix Factorization

09/18/2017
by   Jaedeok Kim, et al.
0

In recent years, a number of artificial intelligent services have been developed such as defect detection system or diagnosis system for customer services. Unfortunately, the core in these services is a black-box in which human cannot understand the underlying decision making logic, even though the inspection of the logic is crucial before launching a commercial service. Our goal in this paper is to propose an analytic method of a model explanation that is applicable to general classification models. To this end, we introduce the concept of a contribution matrix and an explanation embedding in a constraint space by using a matrix factorization. We extract a rule-like model explanation from the contribution matrix with the help of the nonnegative matrix factorization. To validate our method, the experiment results provide with open datasets as well as an industry dataset of a LTE network diagnosis and the results show our method extracts reasonable explanations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/06/2018

A Survey Of Methods For Explaining Black Box Models

In the last years many accurate decision support systems have been const...
research
01/28/2019

Fairwashing: the risk of rationalization

Black-box explanation is the problem of explaining how a machine learnin...
research
05/28/2018

Local Rule-Based Explanations of Black Box Decision Systems

The recent years have witnessed the rise of accurate but obscure decisio...
research
07/09/2019

Nonnegative Matrix Factorization with Local Similarity Learning

Existing nonnegative matrix factorization methods focus on learning glob...
research
10/12/2020

Explaining Neural Matrix Factorization with Gradient Rollback

Explaining the predictions of neural black-box models is an important pr...
research
08/06/2021

Interpretable Summaries of Black Box Incident Triaging with Subgroup Discovery

The need of predictive maintenance comes with an increasing number of in...

Please sign up or login with your details

Forgot password? Click here to reset