Exploring Explainable AI: Current Trends, Challenges, Techniques and its Applications
Article No.: 85, Pages 1 - 9
Abstract
Explainable Artificial Intelligence (XAI) is an emerging field of research that aims to create transparent and interpretable AI models. The recent years have seen a significant increase in the development of XAI methods and techniques, which has led to numerous applications in various domains, including healthcare, finance, and autonomous vehicles. In this paper, the current trends and challenges in XAI, as well as its potential benefits have been reviewed. Also various aspects of XAI, including its definition, importance, challenges, current research trends and importance has presented here. Some of the popular XAI methods, such as LIME, SHAP, and Grad-CAM, and their limitations was highlighted. Moreover, challenges in designing and implementing XAI, including the trade-off between model accuracy and interpretability, the lack of standard evaluation metrics, and the scalability issues of some XAI techniques are addressed. Finally, conclusion is made by emphasizing the importance of continued research and development in XAI to ensure that AI systems are transparent, understandable, and trustworthy.
References
[1]
The Royal Society, "Explainable AI: the basics – POLICY BRIEFING," November 2019, DES6051, 978-1-78252-433-5.
[2]
A. Rai, "Explainable AI: from black box to glass box," J. of the Acad. Mark. Sci., vol. 48, pp. 137–141, 2020.
[3]
R. Saleem, B. Yuan, F. Kurugollu, A. Anjum, and L. Liu, "Explaining deep neural networks: A survey on the global interpretation methods," Neurocomput., vol. 513, no. C, pp. 165–180, Nov. 2022.
[4]
F. K. Došilović, M. Brčić, and N. Hlupić, "Explainable artificial intelligence: A survey," in 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, Croatia, 2018, pp. 0210-0215.
[5]
C. Molnar, G. Casalicchio, and B. Bischl, "Interpretable Machine Learning – A Brief History, State-of-the-Art and Challenges," 2020.
[6]
G. Ras, N. Xie, M. van Gerven, and D. Doran, "Explainable Deep Learning: A Field Guide for the Uninitiated," Journal of Artificial Intelligence Research, vol. 73, pp. 329-397, 2022.
[7]
G. Vilone and L. Longo, "Explainable Artificial Intelligence: a Systematic Review," 2020. https://doi.org/10.48550/arXiv.2006.00093
[8]
M. R. Islam, M. U. Ahmed, S. Barua, and S. Begum, "A Systematic Review of Explainable Artificial Intelligence in Terms of Different Application Domains and Tasks," Applied Sciences, vol. 12, no. 3, p. 1353, 2022.
[9]
M. Danilevsky, K. Qian, R. Aharonov, Y. Katsis, B. Kawas, and P. Sen, "A Survey of the State of Explainable AI for Natural Language Processing," in Proceedings of the 28th International Conference on Computational Linguistics, Suzhou, China, 2020, pp. 447–459. Association for Computational Linguistics.
[10]
R. Guidotti, A. Monreale, F. Turini, D. Pedreschi, and F. Giannotti, "A Survey of Methods for Explaining Black Box Models," ACM Computing Surveys, vol. 51, no. 5, 2018.
[11]
A. Holzinger, P. Kieseberg, and A. M. Tjoa, "From machine learning to explainable AI," in International Cross-Domain Conference for Machine Learning and Knowledge Extraction, 2019, pp. 18-38. Springer.
[12]
A. Rajkomar, E. Oren, K. Chen, A. M. Dai, N. Hajaj, M. Hardt, and P. J. Liu, "Scalable and accurate deep learning with electronic health records," npj Digital Medicine, vol. 1, no. 1, pp. 1-10, 2018.
[13]
A. A. Shih, G. Wu, C. C. Halabi, and M. D. Kohli, "Using artificial intelligence to augment radiologist performance in detecting pulmonary nodules with chest CT," Radiology, vol. 290, no. 1, pp. 92-99, 2019.
[14]
Z. C. Lipton, "The mythos of model interpretability," arXiv preprint arXiv:1606.03490, 2018.
[15]
J. Huang, D. Li, P. Li, L. Liu, and Q. Yang, "Explainable recommendation: A survey and new perspectives," arXiv preprint arXiv:1905.04776, 2019.
[16]
X. Wang, M. Zhang, Y. Cai, and H. Hu, "Explainable search algorithm for E-commerce," in Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2020, pp. 1893-1896.
[17]
Y. Zhang, W. Li, X. Li, and H. Li, "Explainable recommendation algorithm based on attention mechanism," Journal of Ambient Intelligence and Humanized Computing, vol. 12, no. 6, pp. 5991-6001, 2021.
[18]
L. Khrais, "Role of Artificial Intelligence in Shaping Consumer Demand in E-Commerce," Future Internet, vol. 12, p. 226, 2020.
[19]
A. K. M. B. Haque, A. K. M. N. Islam, and P. Mikalef, "Explainable Artificial Intelligence (XAI) from a user perspective: A synthesis of prior literature and problematizing avenues for future research," Technological Forecasting and Social Change, vol. 186, 2022.
[20]
O. Tapalova, N. Zhiyenbayeva, and D. Gura, "Artificial Intelligence in Education: AIEd for Personalized Learning Pathways," Electronic Journal of e-Learning, vol. 20, pp. 639-653, 2022.
[21]
S. Minn, "AI-assisted knowledge assessment techniques for adaptive learning environments," Computers and Education: Artificial Intelligence, vol. 3, p. 100050, 2022.
[22]
Q. Liang, X. Zheng, Y. Wang, and M. Zhu, "O3ERS: An Explainable Recommendation System with Online Learning, Online Recommendation, and Online Explanation," Information Sciences, vol. 562, 2021.
[23]
H. Khosravi, "Explainable Artificial Intelligence in education," Computers and Education: Artificial Intelligence, vol. 3, p. 100074, 2022
[24]
X. Wei, S. Sun, D. Wu, and L. Zhou, "Personalized Online Learning Resource Recommendation Based on Artificial Intelligence and Educational Psychology," Front. Psychol., vol. 12, p. 767837, 2021.
[25]
P. E. de Lange, B. Melsom, C. B. Vennerød, and S. Westgaard, "Explainable AI for Credit Assessment in Banks," Journal of Risk and Financial Management, vol. 15, no. 12, p. 556, 2022.
[26]
P. Weber, K. V. Carl, and O. Hinz, "Applications of Explainable Artificial Intelligence in Finance—a systematic review of Finance, Info. Systems, and Computer Science literature," Manag Rev Q, 2023.
[27]
A. Hanif, "Towards Explainable Artificial Intelligence in Banking and Financial Services," Macquarie University, Thesis, 2021
[28]
M. T. Ribeiro, S. Singh, and C. Guestrin, "Why should i trust you?": Explaining the predictions of any classifier, 2016.
[29]
S. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," 2017.
[30]
W. Samek, T. Wiegand, and K.-R. Müller, "Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models," ITU Journal: ICT Discoveries - Special Issue 1 - The Impact of Artificial Intelligence (AI) on Communication Networks and Services, 2017.
[31]
F. Doshi-Velez and B. Kim, "Towards a rigorous science of interpretable machine learning," arXiv:1702.08608, 2017.
[32]
Z. C. Lipton, "The Mythos of Model Interpretability," Queue, vol. 16, pp. 31-57, 2016.
[33]
M. T. Ribeiro, S. Singh, and C. Guestrin, "Anchors: High-Precision Model-Agnostic Explanations," in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1, 2018
[34]
T. Miller, "Explanation in Artificial Intelligence: Insights from the Social Sciences," Artificial Intelligence, vol. 267, pp. 1-38, 2017
[35]
Tayal, M.A.; Deshmukh, M.; Pangave, V.; Joshi, M.; Malwade, S.; Ovale, S. VMLHST: Development of an Efficient Novel Virtual Reality ML Framework with Haptic Feedbacks for Improving Sports Training Scenarios. Int. J. Electr. Electron. Res. 2023, 11, 601–608,
[36]
Khetani, V, Gandhi, Y, Bhattacharya, S, Ajani, S. N, & Limkar, S. (2023). Cross-Domain Analysis of ML and DL: Evaluating their Impact in Diverse Domains. International Journal of Intelligent Systems and Applications in Engineering, 11(7s), 253–262.
[37]
Kerana Hanirex, D., Kaliyamurthie, K.P., Multi-classification approach for detecting thyroid attacks, International Journal of Pharma and Bio Sciences, V-4, I-3, PP: B1246-B1251, 2013
Recommendations
Explainable Artificial Intelligence 101: Techniques, Applications and Challenges
Advanced Intelligent Computing Technology and ApplicationsAbstractArtificial Intelligence (AI) systems have grown commonplace in modern life, with various applications from customized suggestions to self-driving vehicles. As these systems get more complicated, the necessity for transparency in their decision-...
On the role of knowledge graphs in explainable AI
The current hype of Artificial Intelligence (AI) mostly refers to the success of machine learning and its sub-domain of deep learning. However, AI is also about other areas, such as Knowledge Representation and Reasoning, or Distributed AI, i.e., areas ...
DARPA's explainable artificial intelligence (XAI) program
IUI '19: Proceedings of the 24th International Conference on Intelligent User InterfacesThe DARPA's Explainable Artificial Intelligence (XAI) program endeavors to create AI systems whose learned models and decisions can be understood and appropriately trusted by end users. This talk will summarize the XAI program and present highlights ...
Comments
Information & Contributors
Information
Published In
November 2023
1215 pages
ISBN:9798400709418
DOI:10.1145/3647444
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 13 May 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICIMMI 2023
ICIMMI 2023: International Conference on Information Management & Machine Intelligence
November 23 - 25, 2023
Jaipur, India
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 124Total Downloads
- Downloads (Last 12 months)124
- Downloads (Last 6 weeks)11
Reflects downloads up to 05 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format