A review of feature selection strategies utilizing graph data structures and knowledge graphs

TL;DR

This review comprehensively examines feature selection strategies in Knowledge Graphs, emphasizing their importance in improving model performance, interpretability, and scalability across various domains, and highlights future research directions.

Contribution

It provides a detailed survey of existing methods, emphasizing the integration of domain knowledge, multi-objective optimization, and explainable AI in KG feature selection.

Findings

Highlighting the importance of scalability and accuracy in feature selection

Identifying the potential of multi-objective optimization and interdisciplinary approaches

Outlining future directions for dynamic and explainable KG feature selection

Abstract

Feature selection in Knowledge Graphs (KGs) are increasingly utilized in diverse domains, including biomedical research, Natural Language Processing (NLP), and personalized recommendation systems. This paper delves into the methodologies for feature selection within KGs, emphasizing their roles in enhancing machine learning (ML) model efficacy, hypothesis generation, and interpretability. Through this comprehensive review, we aim to catalyze further innovation in feature selection for KGs, paving the way for more insightful, efficient, and interpretable analytical models across various domains. Our exploration reveals the critical importance of scalability, accuracy, and interpretability in feature selection techniques, advocating for the integration of domain knowledge to refine the selection process. We highlight the burgeoning potential of multi-objective optimization and interdisciplinary collaboration in advancing KG feature selection, underscoring the transformative impact of such methodologies on precision medicine, among other fields. The paper concludes by charting future directions, including the development of scalable, dynamic feature selection algorithms and the integration of explainable AI principles to foster transparency and trust in KG-driven models.