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
  • [41] Interpretable machine learning methods for predictions in systems biology from omics data
    Sidak, David
    Schwarzerova, Jana
    Weckwerth, Wolfram
    Waldherr, Steffen
    FRONTIERS IN MOLECULAR BIOSCIENCES, 2022, 9
  • [42] Exploring high thermal conductivity polymers via interpretable machine learning with physical descriptors
    Xiang Huang
    Shengluo Ma
    C. Y. Zhao
    Hong Wang
    Shenghong Ju
    npj Computational Materials, 9
  • [43] Exploring Trajectory Prediction Through Machine Learning Methods
    Wang, Chujie
    Ma, Lin
    Li, Rongpeng
    Durrani, Tariq S.
    Zhang, Honggang
    IEEE ACCESS, 2019, 7 : 101441 - 101452
  • [44] Mortality Risk Evaluation: A Proposal for Intensive Care Units Patients Exploring Machine Learning Methods
    Rodrigues de Souza, Alexandre Renato
    Ferreira, Fabricio Neitzke
    Lambrecht, Rodrigo Blanke
    Reichow, Leonardo Costa
    Santos, Helida Salles
    Sander Reiser, Renata Hax
    Yamin, Adenauer Correa
    INTELLIGENT SYSTEMS, PT I, 2022, 13653 : 1 - 14
  • [45] Interpretable machine learning in bioinformatics Introduction
    Cho, Young-Rae
    Kang, Mingon
    METHODS, 2020, 179 : 1 - 2
  • [46] Survey and Evaluation of Hypertension Machine Learning Research
    du Toit, Clea
    Tran, Tran Quoc Bao
    Deo, Neha
    Aryal, Sachin
    Lip, Stefanie
    Sykes, Robert
    Manandhar, Ishan
    Sionakidis, Aristeidis
    Stevenson, Leah
    Pattnaik, Harsha
    Alsanosi, Safaa
    Kassi, Maria
    Le, Ngoc
    Rostron, Maggie
    Nichol, Sarah
    Aman, Alisha
    Nawaz, Faisal
    Mehta, Dhruven
    Tummala, Ramakumar
    McCallum, Linsay
    Reddy, Sandeep
    Visweswaran, Shyam
    Kashyap, Rahul
    Joe, Bina
    Padmanabhan, Sandosh
    JOURNAL OF THE AMERICAN HEART ASSOCIATION, 2023, 12 (09):
  • [47] A Survey on Trust Evaluation Based on Machine Learning
    Wang, Jingwen
    Jing, Xuyang
    Yan, Zheng
    Fu, Yulong
    Pedrycz, Witold
    Yang, Laurence T.
    ACM COMPUTING SURVEYS, 2020, 53 (05)
  • [48] Interpretable machine learning with reject option
    Brinkrolf, Johannes
    Hammer, Barbara
    AT-AUTOMATISIERUNGSTECHNIK, 2018, 66 (04) : 283 - 290
  • [49] Interpretable discovery of semiconductors with machine learning
    Hitarth Choubisa
    Petar Todorović
    Joao M. Pina
    Darshan H. Parmar
    Ziliang Li
    Oleksandr Voznyy
    Isaac Tamblyn
    Edward H. Sargent
    npj Computational Materials, 9
  • [50] Interpretable machine learning for perturbation biology
    Shen, Judy
    Yuan, Bo
    Luna, Augustin
    Korkut, Anil
    Marks, Debora
    Ingraham, John
    Sander, Chris
    CANCER RESEARCH, 2020, 80 (16)