Confidential — Stefan Michaelcheck Only

A Review of Knowledge Graphs: Modern Frameworks, Applications, and Open Challenges

2026field synthesisorganizationalsurvey

Kumkum Saxena, Gaurav Kukdeja, Arohi Jambenal, Piyush Hingorani

Lecture notes in networks and systems

https://doi.org/10.1007/978-3-032-13803-3_7OpenAlex: W7125821431
1
URLs Found
0
Internal Citations
4
Authors
usable
Abstract Quality
GPT-5.5 Abstract Analysis

Problems Identified (5)

KG construction and deployment complexity: Knowledge graph frameworks and deployment span manual curation, automatic extraction, and hybrid paradigms that require review and comparison.

KG scalability and interoperability challenges: Knowledge graphs face challenges including data sparsity, computational complexity, standardization, and multimodal data integration.

Compound SPARQL query difficulty: Even strong models struggle to handle compound SPARQL queries effectively over RDF-based knowledge graphs.

KG construction and deployment complexity: Knowledge graph frameworks and deployment span manual curation, automatic extraction, and hybrid paradigms that require review and comparison.

KG scalability and interoperability challenges: Knowledge graphs face challenges including data sparsity, computational complexity, standardization, and multimodal data integration.

Proposed Solutions (5)

KG frameworks and deployment review: The paper reviews knowledge graph frameworks and deployment methods across manual, automatic, and hybrid construction paradigms.

LLM-KG integration review: The paper investigates integration of knowledge graphs with large language models and discusses contributions to knowledge representation, entity resolution, and context-aware retrieval.

KG research agenda: The paper identifies future research directions such as multimodal knowledge fusion, query execution optimization, and self-adapting knowledge graphs.

Recent KG literature review: The paper provides a synopsis of knowledge graphs and reviews methodologies, frameworks, and recent achievements from the last three years.

KG frameworks and deployment review: The paper reviews knowledge graph frameworks and deployment methods across manual, automatic, and hybrid construction paradigms.

Results (3)

KG AI application coverage:

KG integration benefits:

LLM support and SPARQL limitation:

Research Domain

Knowledge graphs and AI applications

← Back to all papers