Exploring Evaluation Methods for Interpretable Machine Learning: A Survey

被引:8
|
作者
Alangari, Nourah [1 ]
Menai, Mohamed El Bachir [1 ]
Mathkour, Hassan [1 ]
Almosallam, Ibrahim [2 ]
机构
[1] King Saud Univ, Coll Comp & Informat Sci, Dept Comp Sci, Riyadh 11543, Saudi Arabia
[2] Saudi Informat Technol Co SITE, Riyadh 12382, Saudi Arabia
关键词
interpretability; explainable AI; evaluating interpretability; BLACK-BOX; RULES; CLASSIFICATION; ACCURACY; ISSUES;
D O I
10.3390/info14080469
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In recent times, the progress of machine learning has facilitated the development of decision support systems that exhibit predictive accuracy, surpassing human capabilities in certain scenarios. However, this improvement has come at the cost of increased model complexity, rendering them black-box models that obscure their internal logic from users. These black boxes are primarily designed to optimize predictive accuracy, limiting their applicability in critical domains such as medicine, law, and finance, where both accuracy and interpretability are crucial factors for model acceptance. Despite the growing body of research on interpretability, there remains a significant dearth of evaluation methods for the proposed approaches. This survey aims to shed light on various evaluation methods employed in interpreting models. Two primary procedures are prevalent in the literature: qualitative and quantitative evaluations. Qualitative evaluations rely on human assessments, while quantitative evaluations utilize computational metrics. Human evaluation commonly manifests as either researcher intuition or well-designed experiments. However, this approach is susceptible to human biases and fatigue and cannot adequately compare two models. Consequently, there has been a recent decline in the use of human evaluation, with computational metrics gaining prominence as a more rigorous method for comparing and assessing different approaches. These metrics are designed to serve specific goals, such as fidelity, comprehensibility, or stability. The existing metrics often face challenges when scaling or being applied to different types of model outputs and alternative approaches. Another important factor that needs to be addressed is that while evaluating interpretability methods, their results may not always be entirely accurate. For instance, relying on the drop in probability to assess fidelity can be problematic, particularly when facing the challenge of out-of-distribution data. Furthermore, a fundamental challenge in the interpretability domain is the lack of consensus regarding its definition and requirements. This issue is compounded in the evaluation process and becomes particularly apparent when assessing comprehensibility.
引用
收藏
页数:29
相关论文
共 50 条
  • [1] A Survey of Interpretable Machine Learning Methods
    Wang, Yan
    Tuerhong, Gulanbaier
    2022 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY, HUMAN-COMPUTER INTERACTION AND ARTIFICIAL INTELLIGENCE, VRHCIAI, 2022, : 232 - 237
  • [2] Interpretable Machine Learning Tools: A Survey
    Agarwal, Namita
    Das, Saikat
    2020 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2020, : 1528 - 1534
  • [3] Taxonomy and Survey of Interpretable Machine Learning Method
    Das, Saikat
    Agarwal, Namita
    Venugopal, Deepak
    Sheldon, Frederick T.
    Shiva, Sajjan
    2020 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2020, : 670 - 677
  • [4] Definitions, methods, and applications in interpretable machine learning
    Murdoch, W. James
    Singh, Chandan
    Kumbier, Karl
    Abbasi-Asl, Reza
    Yu, Bin
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2019, 116 (44) : 22071 - 22080
  • [5] Interpretable Combinatorial Machine Learning-Based Shale Fracability Evaluation Methods
    Wang, Di
    Jiao, Dingyu
    Zhang, Zihang
    Zhou, Runze
    Guo, Weize
    Su, Huai
    ENERGIES, 2025, 18 (01)
  • [6] Kernel methods for interpretable machine learning of order parameters
    Ponte, Pedro
    Melko, Roger G.
    PHYSICAL REVIEW B, 2017, 96 (20)
  • [7] Interpretable Machine Learning
    Chen V.
    Li J.
    Kim J.S.
    Plumb G.
    Talwalkar A.
    Queue, 2021, 19 (06): : 28 - 56
  • [8] Predicting Hurricane Evacuation Decisions with Interpretable Machine Learning Methods
    Yuran Sun
    Shih-Kai Huang
    Xilei Zhao
    International Journal of Disaster Risk Science, 2024, 15 : 134 - 148
  • [9] Interpretable machine learning methods for in vitro pharmaceutical formulation development
    Ye, Zhuyifan
    Yang, Wenmian
    Yang, Yilong
    Ouyang, Defang
    FOOD FRONTIERS, 2021, 2 (02): : 195 - 207
  • [10] Predicting Hurricane Evacuation Decisions with Interpretable Machine Learning Methods
    Yuran Sun
    Shih-Kai Huang
    Xilei Zhao
    InternationalJournalofDisasterRiskScience, 2024, 15 (01) : 134 - 148