Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations

被引：0

作者：

Aslansefat, Koorosh ^{[1
]}

Hashemian, Mojgan ^{[2
]}

Walker, Martin ^{[1
]}

Akram, Mohammed Naveed ^{[3
]}

Sorokos, Ioannis ^{[3
]}

Papadopoulos, Yiannis ^{[4
]}

机构：

[1] Univ Hull, Comp Sci, Kingston Upon Hull HU6 7RX, England

[2] Direct Line Grp Ltd, Leeds LS1 4AZ, England

[3] Fraunhofer Inst Expt Software Engn, D-67663 Kaiserslautern, Germany

[4] Univ Hull, Dependable Intelligent Syst Res Grp, Kingston Upon Hull HU6 7RX, England

来源：

IEEE SOFTWARE | 2024年 / 41卷 / 01期

关键词：

Closed Box; Perturbation Methods; Predictive Models; Gaussian Distribution; Data Models; Machine Learning; Training; Object Object; Use Of Measures; Statistical Measures; Wide Range Of Domains; Growth In Recent Years; Statistical Distance; Variety Of Supports; Linear Model Object Object; Alternative Models Object Object; Model Coefficients; Maximum Distance; Intersection Over Union Object Object Object Object Object Object; Kernel Function; Input Samples; Light Signal Object Object; Part Of The Image; Adversarial Attacks; Random Perturbations; Perturbation Vector; Human Intuition; Game Theory Object Object; Understanding Of Models;

D O I：

10.1109/MS.2023.3321282

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Explainability is a key aspect of improving trustworthiness. We therefore propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.

引用

页码：87 / 97

页数：11

共 50 条

[11] Model-Agnostic Counterfactual Explanations in Credit Scoring
Dastile, Xolani
Celik, Turgay
Vandierendonck, Hans
IEEE ACCESS, 2022, 10 : 69543 - 69554
[12] On the Granularity of Explanations in Model Agnostic NLP Interpretability
Rychener, Yves
Renard, Xavier
Seddah, Djame
Frossard, Pascal
Detyniecki, Marcin
MACHINE LEARNING AND PRINCIPLES AND PRACTICE OF KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2022, PT I, 2023, 1752 : 498 - 512
[13] Model-Agnostic Counterfactual Explanations for Consequential Decisions
Karimi, Amir-Hossein
Barthe, Gilles
Balle, Borja
Valera, Isabel
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 895 - 904
[14] Semantic Reasoning from Model-Agnostic Explanations
Perdih, Timen Stepisnik
Lavrac, Nada
Skrlj, Blaz
2021 IEEE 19TH WORLD SYMPOSIUM ON APPLIED MACHINE INTELLIGENCE AND INFORMATICS (SAMI 2021), 2021, : 105 - 110
[15] A novel dataset and local interpretable model-agnostic explanations (LIME) for monkeypox prediction
Sharma, Nonita
Mohanty, Sachi Nandan
Mahato, Shalini
Pattanaik, Chinmaya Ranjan
INTELLIGENT DECISION TECHNOLOGIES-NETHERLANDS, 2023, 17 (04): : 1297 - 1308
[16] Sharpening Local Interpretable Model-Agnostic Explanations for Histopathology: Improved Understandability and Reliability
Graziani, Mara
de Sousa, Iam Palatnik
Vellasco, Marley M. B. R.
da Silva, Eduardo Costa
Muller, Henning
Andrearczyk, Vincent
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT III, 2021, 12903 : 540 - 549
[17] On the transferability of local model-agnostic explanations of machine learning models to unseen data
Lopez Gonzalez, Alba Maria
Garcia-Cuesta, Esteban
IEEE CONFERENCE ON EVOLVING AND ADAPTIVE INTELLIGENT SYSTEMS 2024, IEEE EAIS 2024, 2024, : 243 - 252
[18] Model-agnostic and diverse explanations for streaming rumour graphs
Nguyen, Thanh Tam
Phan, Thanh Cong
Nguyen, Minh Hieu
Weidlich, Matthias
Yin, Hongzhi
Jo, Jun
Nguyen, Quoc Viet Hung
KNOWLEDGE-BASED SYSTEMS, 2022, 253
[19] Anchors: High-Precision Model-Agnostic Explanations
Ribeiro, Marco Tulio
Singh, Sameer
Guestrin, Carlos
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 1527 - 1535
[20] Model-Agnostic Explanations using Minimal Forcing Subsets
Han, Xing
Ghosh, Joydeep
2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,

← 1 2 3 4 5 →