Sufficient reasons for classifier decisions in the presence of constraints

05/12/2021
by   Niku Gorji, et al.
0

Recent work has unveiled a theory for reasoning about the decisions made by binary classifiers: a classifier describes a Boolean function, and the reasons behind an instance being classified as positive are the prime-implicants of the function that are satisfied by the instance. One drawback of these works is that they do not explicitly treat scenarios where the underlying data is known to be constrained, e.g., certain combinations of features may not exist, may not be observable, or may be required to be disregarded. We propose a more general theory, also based on prime-implicants, tailored to taking constraints into account. The main idea is to view classifiers in the presence of constraints as describing partial Boolean functions, i.e., that are undefined on instances that do not satisfy the constraints. We prove that this simple idea results in reasons that are no less (and sometimes more) succinct. That is, not taking constraints into account (e.g., ignored, or taken as negative instances) results in reasons that are subsumed by reasons that do take constraints into account. We illustrate this improved parsimony on synthetic classifiers and classifiers learned from real data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/21/2020

On The Reasons Behind Decisions

Recent work has shown that some common machine learning classifiers can ...
research
04/28/2023

A New Class of Explanations for Classifiers with Non-Binary Features

Two types of explanations have received significant attention in the lit...
research
10/20/2022

Modelling and Explaining Legal Case-based Reasoners through Classifiers

This paper brings together two lines of research: factor-based models of...
research
01/30/2023

On the Complexity of Enumerating Prime Implicants from Decision-DNNF Circuits

We consider the problem EnumIP of enumerating prime implicants of Boolea...
research
05/09/2022

Galois theory for analogical classifiers

Analogical proportions are 4-ary relations that read "A is to B as C is ...
research
06/29/2018

Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints

Classifiers can be trained with data-dependent constraints to satisfy fa...
research
10/06/2021

Reconsidering Optimistic Algorithms for Relational DBMS

At DBKDA 2019, we demonstrated that StrongDBMS with simple but rigorous ...

Please sign up or login with your details

Forgot password? Click here to reset