Knowledge-graph-based explainable AI: A systematic review

Объяснимый искусственный интеллект на основе графов знаний: систематический обзор
Enayat Rajabi, Kobra Etminani
2022-09-24

KG reasoningexplainable AIhealthcareknowledge graphssystematic review
In recent years, knowledge graphs (KGs) have been widely applied in various domains for different purposes. The semantic model of KGs can represent knowledge through a hierarchical structure based on classes of entities, their properties, and their relationships. The construction of large KGs can enable the integration of heterogeneous information sources and help Artificial Intelligence (AI) systems be more explainable and interpretable. This systematic review examines a selection of recent publications to understand how KGs are currently being used in eXplainable AI systems. To achieve this goal, we design a framework and divide the use of KGs into four categories: extracting features, extracting relationships, constructing KGs, and KG reasoning. We also identify where KGs are mostly used in eXplainable AI systems (pre-model, in-model, and post-model) according to the aforementioned categories. Based on our analysis, KGs have been mainly used in pre-model XAI for feature and relation extraction. They were also utilised for inference and reasoning in post-model XAI. We found several studies that leveraged KGs to explain the XAI models in the healthcare domain.
1
In post-model explainable AI, knowledge graphs are used primarily for inference and reasoning to support explanations.
2
Knowledge graphs are mainly used in pre-model explainable AI systems for extracting features and relationships.
3
Knowledge graphs support explainability by integrating heterogeneous information through semantic representations of entities, properties, and relationships.
4
Several reviewed studies use knowledge graphs to explain AI models in the healthcare domain.
5
The systematic review proposes a framework categorizing knowledge-graph use in explainable AI into feature extraction, relationship extraction, KG construction, and KG reasoning.

knowledge graphs used in explainable AI systems

the roles and usage patterns of knowledge graphs in XAI, including feature and relationship extraction, knowledge-graph construction, reasoning, and model-stage deployment

Publication Details
Publication Date
2022-09-24
Journal
Journal of Information Science
Publisher
SAGE Publishing
ISSN
0165-5515
Cited by
222
Access Type
Author Information
Authors
Enayat Rajabi
Kobra Etminani
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%