EUVIMEDSkopri EUVIMED
ÜbersichtsarbeitSystematische ÜbersichtOpen access

Explainable AI Approaches in Federated Learning: Systematic Review

Titus Tunduny iD, Bernard Shibwabo iD

JMIR AI · 2026-02-03 · 5 · e69985

DOI: 10.2196/69985 ↗

At a glance

Übersichtsarbeit in JMIR AI, published online on 2026-02-03. Written by Titus Tunduny and 1 co-authors. Institution: School of Computing & Engineering Sciences, Strathmore University, Nairobi, Kenya. Cited 14 times so far (Crossref); 82 references. The full text is freely available in PubMed Central.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Artificial intelligence (AI) has, in the recent past, experienced a rebirth with the growth of generative AI systems such as ChatGPT and Bard. These systems are trained with billions of parameters and have enabled widespread accessibility and understanding of AI among different user groups. Widespread adoption of AI has led to the need for understanding how machine learning (ML) models operate to build trust in them. An understanding of how these models generate their results remains a huge challenge that explainable AI seeks to solve. Federated learning (FL) grew out of the need to have privacy-preserving AI by having ML models that are decentralized but still share model parameters with a global model.

Objective

This study sought to examine the extent of development of the explainable AI field within the FL environment in relation to the main contributions made, the types of FL, the sectors it is applied to, the models used, the methods applied by each study, and the databases from which sources are obtained.

Methods

A systematic search in 8 electronic databases, namely, Web of Science Core Collection, Scopus, PubMed, ACM Digital Library, IEEE Xplore, Mendeley, BASE, and Google Scholar, was undertaken.

Results

A review of 26 studies revealed that research on explainable FL is steadily growing despite being concentrated in Europe and Asia. The key determinants of FL use were data privacy and limited training data. Horizontal FL remains the preferred approach for federated ML, whereas post hoc explainability techniques were preferred.

Conclusions

There is potential for development of novel approaches and improvement of existing approaches in the explainable FL field, especially for critical areas. Trial Registration OSF Registries 10.17605/OSF.IO/Y85WA; https://osf.io/y85wa

Subjects

Author keywords

explainable artificial intelligenceexplainable federated artificial intelligencefederated learningmodel interpretabilityprivacy-preserving machine learning

Authors and institutions

  • School of Computing & Engineering Sciences, Strathmore University, Nairobi, Kenya.

ORCID profiles: Titus Tunduny, Bernard Shibwabo

Cite

APA

Tunduny, T., & Shibwabo, B. (2026). Explainable AI Approaches in Federated Learning: Systematic Review. JMIR AI, 5, e69985. https://doi.org/10.2196/69985

Vancouver

Tunduny T, Shibwabo B. Explainable AI Approaches in Federated Learning: Systematic Review. JMIR AI. 2026;5:e69985. doi:10.2196/69985

BibTeX
@article{Tunduny2026,
  author = {Tunduny, Titus and Shibwabo, Bernard},
  title = {Explainable AI Approaches in Federated Learning: Systematic Review},
  journal = {JMIR AI},
  year = {2026},
  volume = {5},
  pages = {e69985},
  doi = {10.2196/69985}
}
Start for free →