Saved in:
Bibliographic Details
Main Authors: Konstantinov, Andrei V., Kozlov, Boris V., Kirpichenko, Stanislav R., Utkin, Lev V.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.16294
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913213950459904
author Konstantinov, Andrei V.
Kozlov, Boris V.
Kirpichenko, Stanislav R.
Utkin, Lev V.
author_facet Konstantinov, Andrei V.
Kozlov, Boris V.
Kirpichenko, Stanislav R.
Utkin, Lev V.
contents A new approach to the local and global explanation is proposed. It is based on selecting a convex hull constructed for the finite number of points around an explained instance. The convex hull allows us to consider a dual representation of instances in the form of convex combinations of extreme points of a produced polytope. Instead of perturbing new instances in the Euclidean feature space, vectors of convex combination coefficients are uniformly generated from the unit simplex, and they form a new dual dataset. A dual linear surrogate model is trained on the dual dataset. The explanation feature importance values are computed by means of simple matrix calculations. The approach can be regarded as a modification of the well-known model LIME. The dual representation inherently allows us to get the example-based explanation. The neural additive model is also considered as a tool for implementing the example-based explanation approach. Many numerical experiments with real datasets are performed for studying the approach. The code of proposed algorithms is available.
format Preprint
id arxiv_https___arxiv_org_abs_2401_16294
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dual feature-based and example-based explanation methods
Konstantinov, Andrei V.
Kozlov, Boris V.
Kirpichenko, Stanislav R.
Utkin, Lev V.
Machine Learning
Artificial Intelligence
A new approach to the local and global explanation is proposed. It is based on selecting a convex hull constructed for the finite number of points around an explained instance. The convex hull allows us to consider a dual representation of instances in the form of convex combinations of extreme points of a produced polytope. Instead of perturbing new instances in the Euclidean feature space, vectors of convex combination coefficients are uniformly generated from the unit simplex, and they form a new dual dataset. A dual linear surrogate model is trained on the dual dataset. The explanation feature importance values are computed by means of simple matrix calculations. The approach can be regarded as a modification of the well-known model LIME. The dual representation inherently allows us to get the example-based explanation. The neural additive model is also considered as a tool for implementing the example-based explanation approach. Many numerical experiments with real datasets are performed for studying the approach. The code of proposed algorithms is available.
title Dual feature-based and example-based explanation methods
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.16294