Announcements

To showcase recent progress in explainable artificial intelligence (XAI), Machine Learning and Knowledge Extraction (MAKE, ISSN: 2504-4990) is pleased to present a curated list of thirteen highlight papers published in 2024.

These works cover key areas such as Shapley additive explanations (SHAP), Grad-CAM, LIME, and cognitive load theory. The methods have been applied across rolling bearing fault diagnosis, medical imaging, cybersecurity, and educational AI, advancing the field toward more transparent, reliable, and responsible intelligent systems.

We hope this selection offers a clear snapshot of current research trends and provides inspiration for further exploration in explainable artificial intelligence.

1. “Cross-Validation Visualized: A Narrative Guide to Advanced Methods”
by Johannes Allgaier and Rüdiger Pryss
Mach. Learn. Knowl. Extr. 2024, 6(2), 1378-1388; https://doi.org/10.3390/make6020065
Available online: https://www.mdpi.com/2504-4990/6/2/65

2. “SHapley Additive exPlanations (SHAP) for Efficient Feature Selection in Rolling Bearing Fault Diagnosis”
by Mailson Ribeiro Santos, Affonso Guedes and Ignacio Sanchez-Gendriz
Mach. Learn. Knowl. Extr. 2024, 6(1), 316-341; https://doi.org/10.3390/make6010016
Available online: https://www.mdpi.com/2504-4990/6/1/16

3. “Empowering Brain Tumor Diagnosis through Explainable Deep Learning”
by Zhengkun Li and Omar Dib
Mach. Learn. Knowl. Extr. 2024, 6(4), 2248-2281; https://doi.org/10.3390/make6040111
Available online: https://www.mdpi.com/2504-4990/6/4/111

4. “A Cognitive Load Theory (CLT) Analysis of Machine Learning Explainability, Transparency, Interpretability, and Shared Interpretability”
by Stephen Fox and Vitor Fortes Rey
Mach. Learn. Knowl. Extr. 2024, 6(3), 1494-1509; https://doi.org/10.3390/make6030071
Available online: https://www.mdpi.com/2504-4990/6/3/71

5. “Uncertainty in XAI: Human Perception and Modeling Approaches”
by Teodor Chiaburu, Frank Haußer and Felix Bießmann
Mach. Learn. Knowl. Extr. 2024, 6(2), 1170-1192; https://doi.org/10.3390/make6020055
Available online: https://www.mdpi.com/2504-4990/6/2/55

6. “Climate Change and Soil Health: Explainable Artificial Intelligence Reveals Microbiome Response to Warming”
by Pierfrancesco Novielli, Michele Magarelli, Donato Romano, Lorenzo de Trizio, Pierpaolo Di Bitonto, Alfonso Monaco, Nicola Amoroso, Anna Maria Stellacci, Claudia Zoani, Roberto Bellotti et al.
Mach. Learn. Knowl. Extr. 2024, 6(3), 1564-1578; https://doi.org/10.3390/make6030075
Available online: https://www.mdpi.com/2504-4990/6/3/75

7. “Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification”
by Xinyu (Freddie) Liu, Gizem Karagoz and Nirvana Meratnia
Mach. Learn. Knowl. Extr. 2025, 7(1), 1; https://doi.org/10.3390/make7010001
Available online: https://www.mdpi.com/2504-4990/7/1/1

8. “Tertiary Review on Explainable Artificial Intelligence: Where Do We Stand?”
by Frank van Mourik, Annemarie Jutte, Stijn E. Berendse, Faiza A. Bukhsh and Faizan Ahmed
Mach. Learn. Knowl. Extr. 2024, 6(3), 1997-2017; https://doi.org/10.3390/make6030098
Available online: https://www.mdpi.com/2504-4990/6/3/98

9. “Assessment of Software Vulnerability Contributing Factors by Model-Agnostic Explainable AI”
by Ding Li, Yan Liu and Jun Huang
Mach. Learn. Knowl. Extr. 2024, 6(2), 1087-1113; https://doi.org/10.3390/make6020050
Available online: https://www.mdpi.com/2504-4990/6/2/50

10. “Reliable and Faithful Generative Explainers for Graph Neural Networks”
by Yiqiao Li, Jianlong Zhou, Boyuan Zheng, Niusha Shafiabady and Fang Chen
Mach. Learn. Knowl. Extr. 2024, 6(4), 2913-2929; https://doi.org/10.3390/make6040139
Available online: https://www.mdpi.com/2504-4990/6/4/139

11. “A Novel Integration of Data-Driven Rule Generation and Computational Argumentation for Enhanced Explainable AI”
by Lucas Rizzo, Damiano Verda, Serena Berretta and Luca Longo
Mach. Learn. Knowl. Extr. 2024, 6(3), 2049-2073; https://doi.org/10.3390/make6030101
Available online: https://www.mdpi.com/2504-4990/6/3/101

12. “Why Do Tree Ensemble Approximators Not Outperform the Recursive-Rule eXtraction Algorithm?”
by Soma Onishi, Masahiro Nishimura, Ryota Fujimura and Yoichi Hayashi
Mach. Learn. Knowl. Extr. 2024, 6(1), 658-678; https://doi.org/10.3390/make6010031
Available online: https://www.mdpi.com/2504-4990/6/1/31