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

[41] Generating structural alerts from toxicology datasets using the local interpretable model-agnostic explanations method
Nascimento, Cayque Monteiro Castro
Moura, Paloma Guimaraes
Pimentel, Andre Silva
DIGITAL DISCOVERY, 2023, 2 (05): : 1311 - 1325
[42] Foreign direct investment and local interpretable model-agnostic explanations: a rational framework for FDI decision making
Singh, Devesh
JOURNAL OF ECONOMICS FINANCE AND ADMINISTRATIVE SCIENCE, 2024, 29 (57): : 98 - 120
[43] Model-agnostic vs. Model-intrinsic Interpretability for Explainable Product Search
Ai, Qingyao
Narayanan, Lakshmi R.
PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 5 - 15
[44] MANE: Model-Agnostic Non-linear Explanations for Deep Learning Model
Tian, Yue
Liu, Guanjun
2020 IEEE WORLD CONGRESS ON SERVICES (SERVICES), 2020, : 33 - 36
[45] ILIME: Local and Global Interpretable Model-Agnostic Explainer of Black-Box Decision
ElShawi, Radwa
Sherif, Youssef
Al-Mallah, Mouaz
Sakr, Sherif
ADVANCES IN DATABASES AND INFORMATION SYSTEMS, ADBIS 2019, 2019, 11695 : 53 - 68
[46] Evaluating MASHAP as a faster alternative to LIME for model-agnostic machine learning interpretability
Messalas, Andreas
Aridas, Christos
Kanellopoulos, Yannis
2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2020, : 5777 - 5779
[47] A comparative study of methods for estimating model-agnostic Shapley value explanations
Olsen, Lars Henry Berge
Glad, Ingrid Kristine
Jullum, Martin
Aas, Kjersti
DATA MINING AND KNOWLEDGE DISCOVERY, 2024, 38 (04) : 1782 - 1829
[48] ELIME: Exact Local Interpretable Model-Agnostic Explanation
Qian, Junyan
Du, Xiaofu
Pan, Ruishi
Ling, Ming
Ding, Hao
EUROPEAN JOURNAL ON ARTIFICIAL INTELLIGENCE, 2025,
[49] MAIRE - A Model-Agnostic Interpretable Rule Extraction Procedure for Explaining Classifiers
Sharma, Rajat
Reddy, Nikhil
Kamakshi, Vidhya
Krishnan, Narayanan C.
Jain, Shweta
MACHINE LEARNING AND KNOWLEDGE EXTRACTION (CD-MAKE 2021), 2021, 12844 : 329 - 349
[50] McXai: Local Model-Agnostic Explanation As Two Games
Huang, Yiran
Schaal, Nicole
Hefenbrock, Michael
Zhou, Yexu
Riedel, Till
Beigl, Michael
2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,

← 1 2 3 4 5 →