Scalable XAI: Towards Explainable Machine Learning Models in Distributed Systems

Ibomoiye Domor Mienye; Theo G. Swart; George Obaido

doi:10.1007/978-3-031-94439-0_1

Scalable XAI: Towards Explainable Machine Learning Models in Distributed Systems

Ibomoiye Domor Mienye, Theo G. Swart, George Obaido

Electrical and Electronic Engineering Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The application of artificial intelligence (AI) has grown significantly due to recent advances in machine learning (ML). However, deploying ML models within distributed computing environments introduces substantial challenges, particularly in terms of scalability and explainability. This review addresses the concept of scalable explainable AI (XAI), focusing on effective methodologies for deploying XAI across various distributed frameworks. The study aims to advance the development of transparent, reliable, and scalable AI applications, thereby ensuring greater trust and broader adoption in diverse operational environments.

Original language	English
Title of host publication	Pan-African Artificial Intelligence and Smart Systems - 3rd Pan-African Conference, PAAISS 2024, Proceedings
Editors	Telex M. N. Ngatched, Isaac Woungang, Jules-Raymond Tapamo, Serestina Viriri
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	3-16
Number of pages	14
ISBN (Print)	9783031944383
DOIs	https://doi.org/10.1007/978-3-031-94439-0_1
Publication status	Published - 2025
Event	3rd Pan-African Conference on Artificial Intelligence and Smart Systems Conference, PAAISS 2024 - Durban, South Africa Duration: 4 Dec 2024 → 6 Dec 2024

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	632 LNICST
ISSN (Print)	1867-8211
ISSN (Electronic)	1867-822X

Conference

Conference	3rd Pan-African Conference on Artificial Intelligence and Smart Systems Conference, PAAISS 2024
Country/Territory	South Africa
City	Durban
Period	4/12/24 → 6/12/24

Keywords

Artificial intelligence
distributed systems
machine learning
XAI

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1007/978-3-031-94439-0_1

Cite this

Mienye, I. D., Swart, T. G., & Obaido, G. (2025). Scalable XAI: Towards Explainable Machine Learning Models in Distributed Systems. In T. M. N. Ngatched, I. Woungang, J.-R. Tapamo, & S. Viriri (Eds.), Pan-African Artificial Intelligence and Smart Systems - 3rd Pan-African Conference, PAAISS 2024, Proceedings (pp. 3-16). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 632 LNICST). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-94439-0_1

Mienye, Ibomoiye Domor ; Swart, Theo G. ; Obaido, George. / Scalable XAI : Towards Explainable Machine Learning Models in Distributed Systems. Pan-African Artificial Intelligence and Smart Systems - 3rd Pan-African Conference, PAAISS 2024, Proceedings. editor / Telex M. N. Ngatched ; Isaac Woungang ; Jules-Raymond Tapamo ; Serestina Viriri. Springer Science and Business Media Deutschland GmbH, 2025. pp. 3-16 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{c7007b94506047248b5913703fa74cfb,

title = "Scalable XAI: Towards Explainable Machine Learning Models in Distributed Systems",

abstract = "The application of artificial intelligence (AI) has grown significantly due to recent advances in machine learning (ML). However, deploying ML models within distributed computing environments introduces substantial challenges, particularly in terms of scalability and explainability. This review addresses the concept of scalable explainable AI (XAI), focusing on effective methodologies for deploying XAI across various distributed frameworks. The study aims to advance the development of transparent, reliable, and scalable AI applications, thereby ensuring greater trust and broader adoption in diverse operational environments.",

keywords = "Artificial intelligence, distributed systems, machine learning, XAI",

author = "Mienye, \{Ibomoiye Domor\} and Swart, \{Theo G.\} and George Obaido",

note = "Publisher Copyright: {\textcopyright} ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2025.; 3rd Pan-African Conference on Artificial Intelligence and Smart Systems Conference, PAAISS 2024 ; Conference date: 04-12-2024 Through 06-12-2024",

year = "2025",

doi = "10.1007/978-3-031-94439-0\_1",

language = "English",

isbn = "9783031944383",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "3--16",

editor = "Ngatched, \{Telex M. N.\} and Isaac Woungang and Jules-Raymond Tapamo and Serestina Viriri",

booktitle = "Pan-African Artificial Intelligence and Smart Systems - 3rd Pan-African Conference, PAAISS 2024, Proceedings",

address = "Germany",

}

Mienye, ID, Swart, TG & Obaido, G 2025, Scalable XAI: Towards Explainable Machine Learning Models in Distributed Systems. in TMN Ngatched, I Woungang, J-R Tapamo & S Viriri (eds), Pan-African Artificial Intelligence and Smart Systems - 3rd Pan-African Conference, PAAISS 2024, Proceedings. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 632 LNICST, Springer Science and Business Media Deutschland GmbH, pp. 3-16, 3rd Pan-African Conference on Artificial Intelligence and Smart Systems Conference, PAAISS 2024, Durban, South Africa, 4/12/24. https://doi.org/10.1007/978-3-031-94439-0_1

Scalable XAI: Towards Explainable Machine Learning Models in Distributed Systems. / Mienye, Ibomoiye Domor; Swart, Theo G.; Obaido, George.
Pan-African Artificial Intelligence and Smart Systems - 3rd Pan-African Conference, PAAISS 2024, Proceedings. ed. / Telex M. N. Ngatched; Isaac Woungang; Jules-Raymond Tapamo; Serestina Viriri. Springer Science and Business Media Deutschland GmbH, 2025. p. 3-16 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 632 LNICST).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Scalable XAI

T2 - 3rd Pan-African Conference on Artificial Intelligence and Smart Systems Conference, PAAISS 2024

AU - Mienye, Ibomoiye Domor

AU - Swart, Theo G.

AU - Obaido, George

N1 - Publisher Copyright: © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2025.

PY - 2025

Y1 - 2025

N2 - The application of artificial intelligence (AI) has grown significantly due to recent advances in machine learning (ML). However, deploying ML models within distributed computing environments introduces substantial challenges, particularly in terms of scalability and explainability. This review addresses the concept of scalable explainable AI (XAI), focusing on effective methodologies for deploying XAI across various distributed frameworks. The study aims to advance the development of transparent, reliable, and scalable AI applications, thereby ensuring greater trust and broader adoption in diverse operational environments.

AB - The application of artificial intelligence (AI) has grown significantly due to recent advances in machine learning (ML). However, deploying ML models within distributed computing environments introduces substantial challenges, particularly in terms of scalability and explainability. This review addresses the concept of scalable explainable AI (XAI), focusing on effective methodologies for deploying XAI across various distributed frameworks. The study aims to advance the development of transparent, reliable, and scalable AI applications, thereby ensuring greater trust and broader adoption in diverse operational environments.

KW - Artificial intelligence

KW - distributed systems

KW - machine learning

KW - XAI

UR - https://www.scopus.com/pages/publications/105013259957

U2 - 10.1007/978-3-031-94439-0_1

DO - 10.1007/978-3-031-94439-0_1

M3 - Conference contribution

AN - SCOPUS:105013259957

SN - 9783031944383

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 3

EP - 16

BT - Pan-African Artificial Intelligence and Smart Systems - 3rd Pan-African Conference, PAAISS 2024, Proceedings

A2 - Ngatched, Telex M. N.

A2 - Woungang, Isaac

A2 - Tapamo, Jules-Raymond

A2 - Viriri, Serestina

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 4 December 2024 through 6 December 2024

ER -

Mienye ID, Swart TG, Obaido G. Scalable XAI: Towards Explainable Machine Learning Models in Distributed Systems. In Ngatched TMN, Woungang I, Tapamo JR, Viriri S, editors, Pan-African Artificial Intelligence and Smart Systems - 3rd Pan-African Conference, PAAISS 2024, Proceedings. Springer Science and Business Media Deutschland GmbH. 2025. p. 3-16. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-031-94439-0_1