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
  • [31] A survey on machine learning methods for churn prediction
    Louis Geiler
    Séverine Affeldt
    Mohamed Nadif
    International Journal of Data Science and Analytics, 2022, 14 : 217 - 242
  • [32] A survey on machine learning methods for churn prediction
    Geiler, Louis
    Affeldt, Severine
    Nadif, Mohamed
    INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS, 2022, 14 (03) : 217 - 242
  • [33] Machine learning and domain decomposition methods - a survey
    Axel Klawonn
    Martin Lanser
    Janine Weber
    Computational Science and Engineering, 1 (1):
  • [34] A Survey of Machine Learning Methods for Big Data
    Ruiz, Zoila
    Salvador, Jaime
    Garcia-Rodriguez, Jose
    BIOMEDICAL APPLICATIONS BASED ON NATURAL AND ARTIFICIAL COMPUTING, PT II, 2017, 10338 : 259 - 267
  • [35] An Interpretable Machine Learning Based Model for Traumatic Severe Pneumothorax Evaluation
    Lv, Y.
    Weng, J.
    Li, J.
    Chen, W.
    Zhao, Y.
    Huang, H.
    INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, 2025, 20 (01)
  • [36] Interpretable Machine Learning Methods for Monitoring Polymer Degradation in Extrusion of Polylactic Acid
    Munir, Nimra
    McMorrow, Ross
    Mulrennan, Konrad
    Whitaker, Darren
    McLoone, Sean
    Kellomaki, Minna
    Talvitie, Elina
    Lyyra, Inari
    McAfee, Marion
    POLYMERS, 2023, 15 (17)
  • [37] Modeling and analysis of droplet generation in microchannels using interpretable machine learning methods
    Liu, Mengqi
    Hu, Haoyang
    Cui, Yongjin
    Song, Jing
    Ma, Li
    Yuan, Zhihong
    Wang, Kai
    Luo, Guangsheng
    CHEMICAL ENGINEERING JOURNAL, 2025, 511
  • [38] Comparison of Machine Learning Methods towards Developing Interpretable Polyamide Property Prediction
    Lee, Franklin Langlang
    Park, Jaehong
    Goyal, Sushmit
    Qaroush, Yousef
    Wang, Shihu
    Yoon, Hong
    Rammohan, Aravind
    Shim, Youngseon
    POLYMERS, 2021, 13 (21)
  • [39] Exploring high thermal conductivity polymers via interpretable machine learning with physical descriptors
    Huang, Xiang
    Ma, Shengluo
    Zhao, C. Y.
    Wang, Hong
    Ju, Shenghong
    NPJ COMPUTATIONAL MATERIALS, 2023, 9 (01)
  • [40] Interpretable and explainable machine learning: A methods-centric overview with concrete examples
    Marcinkevics, Ricards
    Vogt, Julia E.
    WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2023, 13 (03)