Dual feature-based and example-based explanation methods
A new approach to the local and global explanation based on selecting a convex hull constructed for the finite number of points around an explained instance is proposed. The convex hull allows us to consider a dual representation of instances in the form of convex combinations of extreme points of a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2025.1506074/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823860973520289792 |
|---|---|
| author | Andrei Konstantinov Boris Kozlov Stanislav Kirpichenko Lev Utkin Vladimir Muliukha |
| author_facet | Andrei Konstantinov Boris Kozlov Stanislav Kirpichenko Lev Utkin Vladimir Muliukha |
| author_sort | Andrei Konstantinov |
| collection | DOAJ |
| description | A new approach to the local and global explanation based on selecting a convex hull constructed for the finite number of points around an explained instance is proposed. 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. A code of proposed algorithms is available. The proposed results are fundamental and can be used in various application areas. They do not involve specific human subjects and human data. |
| format | Article |
| id | doaj-art-8c0755b0dd0040ca8ed0c2e18003d9fd |
| institution | Kabale University |
| issn | 2624-8212 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj-art-8c0755b0dd0040ca8ed0c2e18003d9fd2025-02-10T06:48:46ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-02-01810.3389/frai.2025.15060741506074Dual feature-based and example-based explanation methodsAndrei KonstantinovBoris KozlovStanislav KirpichenkoLev UtkinVladimir MuliukhaA new approach to the local and global explanation based on selecting a convex hull constructed for the finite number of points around an explained instance is proposed. 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. A code of proposed algorithms is available. The proposed results are fundamental and can be used in various application areas. They do not involve specific human subjects and human data.https://www.frontiersin.org/articles/10.3389/frai.2025.1506074/fullmachine learningexplainable AIneural additive networkdual representationconvex hullexample-based explanation |
| spellingShingle | Andrei Konstantinov Boris Kozlov Stanislav Kirpichenko Lev Utkin Vladimir Muliukha Dual feature-based and example-based explanation methods Frontiers in Artificial Intelligence machine learning explainable AI neural additive network dual representation convex hull example-based explanation |
| title | Dual feature-based and example-based explanation methods |
| title_full | Dual feature-based and example-based explanation methods |
| title_fullStr | Dual feature-based and example-based explanation methods |
| title_full_unstemmed | Dual feature-based and example-based explanation methods |
| title_short | Dual feature-based and example-based explanation methods |
| title_sort | dual feature based and example based explanation methods |
| topic | machine learning explainable AI neural additive network dual representation convex hull example-based explanation |
| url | https://www.frontiersin.org/articles/10.3389/frai.2025.1506074/full |
| work_keys_str_mv | AT andreikonstantinov dualfeaturebasedandexamplebasedexplanationmethods AT boriskozlov dualfeaturebasedandexamplebasedexplanationmethods AT stanislavkirpichenko dualfeaturebasedandexamplebasedexplanationmethods AT levutkin dualfeaturebasedandexamplebasedexplanationmethods AT vladimirmuliukha dualfeaturebasedandexamplebasedexplanationmethods |