Explanations for Monotonic Classifiers

06/01/2021
by   Joao Marques-Silva, et al.
0

In many classification tasks there is a requirement of monotonicity. Concretely, if all else remains constant, increasing (resp. decreasing) the value of one or more features must not decrease (resp. increase) the value of the prediction. Despite comprehensive efforts on learning monotonic classifiers, dedicated approaches for explaining monotonic classifiers are scarce and classifier-specific. This paper describes novel algorithms for the computation of one formal explanation of a (black-box) monotonic classifier. These novel algorithms are polynomial in the run time complexity of the classifier and the number of features. Furthermore, the paper presents a practically efficient model-agnostic algorithm for enumerating formal explanations.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/17/2022

GRAPHSHAP: Motif-based Explanations for Black-box Graph Classifiers

Most methods for explaining black-box classifiers (e.g., on tabular data...
06/30/2016

A Model Explanation System: Latest Updates and Extensions

We propose a general model explanation system (MES) for "explaining" the...
03/05/2021

Compositional Explanations for Image Classifiers

Existing algorithms for explaining the output of image classifiers perfo...
08/13/2020

Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay

Recent work proposed the computation of so-called PI-explanations of Nai...
05/09/2018

A Symbolic Approach to Explaining Bayesian Network Classifiers

We propose an approach for explaining Bayesian network classifiers, whic...
10/21/2018

Label Noise Filtering Techniques to Improve Monotonic Classification

The monotonic ordinal classification has increased the interest of resea...
11/01/2021

Expanding Multi-Market Monopoly and Nonconcavity in the Value of Information

In this paper I investigate a Bayesian inverse problem in the specific s...
This week in AI

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