期刊名： Machine Learning and Knowledge Extraction

期刊主页：https://www.mdpi.com/journal/make

随着人工智能技术的快速发展，可解释性与可信性正成为推动智能系统走向实际应用的重要基础。本专题汇集了发表于 Machine Learning and Knowledge Extraction（MAKE） 的十五篇高被引文章，系统展示了可解释人工智能与可信机器学习领域在2024和2025年的前沿探索与多元视角。研究涵盖可解释AI、模型可解释性、特征选择与优化、基于扰动的解释方法、可解释性方法选择、负责任AI开发、以人为中心的评估、认知负荷理论、教育AI、面部情绪识别伦理、知识管理与AI标准协同等多个方向，重点探讨如何提升机器学习模型的透明度、可理解性与可靠性，并将其拓展应用于医疗健康、网络安全、教育、能源预测、法律及社会信任等领域。这些研究表明，高性能AI系统不仅应追求准确，更需具备可解释性、可靠性，并与人类需求和社会价值相契合。我们期待本专题为构建更透明、更负责任的智能系统提供有益的思路与参考。

1. Advancing AI Interpretability in Medical Imaging: A Comparative Analysis of Pixel-Level Interpretability and Grad-CAM Models

推进医学影像中的AI可解释性：像素级可解释性与Grad-CAM模型的比较分析

https://www.mdpi.com/2504-4990/7/1/12

Ennab, M.; Mcheick, H. Advancing AI Interpretability in Medical Imaging: A Comparative Analysis of Pixel-Level Interpretability and Grad-CAM Models. Mach. Learn. Knowl. Extr. 2025, 7, 12.

2. A Four-Dimensional Analysis of Explainable AI in Energy Forecasting: A Domain-Specific Systematic Review

可解释AI在能源预测中的四维分析：一项领域特定系统综述

https://www.mdpi.com/2504-4990/7/4/153

Arabzadeh, V.; Frank, R. A Four-Dimensional Analysis of Explainable AI in Energy Forecasting: A Domain-Specific Systematic Review. Mach. Learn. Knowl. Extr. 2025, 7, 153.

3. A Multi-Criteria Decision-Making Approach for the Selection of Explainable AI Methods

可解释AI方法选择的多准则决策方法

https://www.mdpi.com/2504-4990/7/4/158

Matejová, M.; Parali?, J. A Multi-Criteria Decision-Making Approach for the Selection of Explainable AI Methods. Mach. Learn. Knowl. Extr. 2025, 7, 158.

4. Quantifying Interdisciplinarity in Scientific Articles Using Deep Learning Toward a TRIZ-Based Framework for Cross-Disciplinary Innovation

基于深度学习的科学文章跨学科性量化及其面向TRIZ的跨学科创新框架

https://www.mdpi.com/2504-4990/7/1/7

Douard, N.; Samet, A.; Giakos, G.; Cavallucci, D. Quantifying Interdisciplinarity in Scientific Articles Using Deep Learning Toward a TRIZ-Based Framework for Cross-Disciplinary Innovation. Mach. Learn. Knowl. Extr. 2025, 7, 7.

5. Behind the Algorithm: International Insights into Data-Driven AI Model Development

算法背后：数据驱动AI模型开发的国际视角

https://www.mdpi.com/2504-4990/7/4/122

Ziv, L.; Nakash, M. Behind the Algorithm: International Insights into Data-Driven AI Model Development. Mach. Learn. Knowl. Extr. 2025, 7, 122.

6. ExShall-CNN: An Explainable Shallow Convolutional Neural Network for Medical Image Segmentation

ExShall-CNN：一种用于医学图像分割的可解释浅层卷积神经网络

https://www.mdpi.com/2504-4990/7/1/19

Khalkhali, V.; Azim, S.M.; Dehzangi, I. ExShall-CNN: An Explainable Shallow Convolutional Neural Network for Medical Image Segmentation. Mach. Learn. Knowl. Extr. 2025, 7, 19.

7. Optimisation-Based Feature Selection for Regression Neural Networks Towards Explainability

面向可解释性的回归神经网络优化特征选择

https://www.mdpi.com/2504-4990/7/2/33

Liapis, G.I.; Tsoka, S.; Papageorgiou, L.G. Optimisation-Based Feature Selection for Regression Neural Networks Towards Explainability. Mach. Learn. Knowl. Extr. 2025, 7, 33.

8. Automated Grading Through Contrastive Learning: A Gradient Analysis and Feature Ablation Approach

基于对比学习的自动评分：梯度分析与特征消融方法

https://www.mdpi.com/2504-4990/7/2/41

Sokac, M.; Fabijaic, M.; Mekterovi?, I.; Mrši?, L. Automated Grading Through Contrastive Learning: A Gradient Analysis and Feature Ablation Approach. Mach. Learn. Knowl. Extr. 2025, 7, 41.

9. More Capable, Less Benevolent: Trust Perceptions of AI Systems across Societal Contexts

能力越强，善意越少？不同社会背景下对AI系统的信任感知

https://www.mdpi.com/2504-4990/6/1/17

Novozhilova, E.; Mays, K.; Paik, S.; Katz, J.E. More Capable, Less Benevolent: Trust Perceptions of AI Systems across Societal Contexts. Mach. Learn. Knowl. Extr. 2024, 6, 342-366.

10. Augmenting Deep Neural Networks with Symbolic Educational Knowledge: Towards Trustworthy and Interpretable AI for Education

用符号化教育知识增强深度神经网络：迈向可信且可解释的教育人工智能

https://www.mdpi.com/2504-4990/6/1/28

Hooshyar, D.; Azevedo, R.; Yang, Y. Augmenting Deep Neural Networks with Symbolic Educational Knowledge: Towards Trustworthy and Interpretable AI for Education. Mach. Learn. Knowl. Extr. 2024, 6, 593-618.

11. Uncertainty in XAI: Human Perception and Modeling Approaches

可解释人工智能中的不确定性：人类感知与建模方法

https://www.mdpi.com/2504-4990/6/2/55

Chiaburu, T.; Haußer, F.; Bießmann, F. Uncertainty in XAI: Human Perception and Modeling Approaches. Mach. Learn. Knowl. Extr. 2024, 6, 1170-1192.

12. Not in My Face: Challenges and Ethical Considerations in Automatic Face Emotion Recognition Technology

别对着我：自动面部情绪识别技术面临的挑战与伦理考量

https://www.mdpi.com/2504-4990/6/4/109

Mattioli, M.; Cabitza, F. Not in My Face: Challenges and Ethical Considerations in Automatic Face Emotion Recognition Technology. Mach. Learn. Knowl. Extr. 2024, 6, 2201-2231.

13. A Cognitive Load Theory (CLT) Analysis of Machine Learning Explainability, Transparency, Interpretability, and Shared Interpretability

基于认知负荷理论的机器学习可解释性、透明度、可理解性与共享可理解性分析

https://www.mdpi.com/2504-4990/6/3/71

Fox, S.; Rey, V.F. A Cognitive Load Theory (CLT) Analysis of Machine Learning Explainability, Transparency, Interpretability, and Shared Interpretability. Mach. Learn. Knowl. Extr. 2024, 6, 1494-1509.

14. Maximising Synergy: The Benefits of a Joint Implementation of Knowledge Management and Artificial Intelligence System Standards

协同增效：知识管理与人工智能系统标准联合实施的优势

https://www.mdpi.com/2504-4990/6/4/112

Khazieva, N.; Pauliková, A.; Chovanová, H.H. Maximising Synergy: The Benefits of a Joint Implementation of Knowledge Management and Artificial Intelligence System Standards. Mach. Learn. Knowl. Extr. 2024, 6, 2282-2302.

15. A Novel Integration of Data-Driven Rule Generation and Computational Argumentation for Enhanced Explainable AI

数据驱动规则生成与计算论证的深度融合：迈向增强的可解释人工智能

https://www.mdpi.com/2504-4990/6/3/101

Rizzo, L.; Verda, D.; Berretta, S.; Longo, L. A Novel Integration of Data-Driven Rule Generation and Computational Argumentation for Enhanced Explainable AI. Mach. Learn. Knowl. Extr. 2024, 6, 2049-2073.

期刊介绍

主编：Prof. Dr. Andreas Holzinger

Machine Learning and Knowledge Extraction (ISSN 2504-4990) 是一个国际型开放获取英文学术期刊，聚焦机器学习和知识提取所有领域相关的研究。期刊发表综述、研究论文、通讯、观点，以及特定主题的特刊。主题领域包括但不限于：机器学习；知识提取；人工智能；神经网络；自然语言处理；无监督学习；隐私保护；不确定性；迁移学习；图像分类；信息检索；特征选择；可视化；基于网络和图的机器学习；几何机器学习与拓扑学；熵及其在机器学习中的应用

2025 Impact Factor：8.4

2025 CiteScore：12.7

Time to First Decision：18.7 Days

Acceptance to Publication：3.8 Days