On Deciding Feature Membership in Explanations of SDD Related Classifiers

02/15/2022
by   Xuanxiang Huang, et al.
0

When reasoning about explanations of Machine Learning (ML) classifiers, a pertinent query is to decide whether some sensitive features can serve for explaining a given prediction. Recent work showed that the feature membership problem (FMP) is hard for Σ_2^P for a broad class of classifiers. In contrast, this paper shows that for a number of families of classifiers, FMP is in NP. Concretely, the paper proves that any classifier for which an explanation can be computed in polynomial time, then deciding feature membership in an explanation can be decided with one NP oracle call. The paper then proposes propositional encodings for classifiers represented with Sentential Decision Diagrams (SDDs) and for other related propositional languages. The experimental results confirm the practical efficiency of the proposed approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/27/2022

Feature Necessity Relevancy in ML Classifier Explanations

Given a machine learning (ML) model and a prediction, explanations can b...
research
06/02/2021

On Efficiently Explaining Graph-Based Classifiers

Recent work has shown that not only decision trees (DTs) may not be inte...
research
04/05/2022

A Set Membership Approach to Discovering Feature Relevance and Explaining Neural Classifier Decisions

Neural classifiers are non linear systems providing decisions on the cla...
research
05/30/2021

A logic for binary classifiers and their explanation

Recent years have witnessed a renewed interest in Boolean function in ex...
research
07/04/2021

Efficient Explanations for Knowledge Compilation Languages

Knowledge compilation (KC) languages find a growing number of practical ...
research
06/01/2021

Efficient Explanations With Relevant Sets

Recent work proposed δ-relevant inputs (or sets) as a probabilistic expl...
research
02/05/2022

A Game-theoretic Understanding of Repeated Explanations in ML Models

This paper formally models the strategic repeated interactions between a...

Please sign up or login with your details

Forgot password? Click here to reset