Earticle

초록

영어

This study develops a systematic, verifiable experimental study to clarify when and how transforming tabular data into graph structures enhances node-level classification: AI-generated synthetic dataset with controlled numbers of nodes, classes, and imbalance; two interpretable graphs are constructed (1) a similarity-based k-nearest neighbors graph with the number of neighbors and model depth varied, and (2) a rule-based graph with explicit, transparent connection rules; and graph-based methods GCN, GraphSAGE to approach this baseline when k and depth are appropriately tuned, before performance saturates or declines due to excessive signal averaging; and rule-based graphs expose architectural differences GraphSAGE is higherperforming and more stable, whereas GCN is more structuresensitive and degrades with depth implying that approaches preserving node-specific information and flexibly aggregating signals are more robust to structural heterogeneity. Overall, the framework offers practical guidance for method selection and graph construction particularly the choice neighbors and depth in a simplified, reproducible form readily extensible to real-world applications.

목차

Abstract
I. INTRODUCTION
II. OBJECTIVES
III. RESEARCH METHODOLOGY
A. Dataset
B. Graph Construction
C. Comparative models
D. Experimental Design
E. Evaluation
IV. RESULTS
A. Case without Graph
B. Rule-Based Graph
C. Similarity-Based Graph and the Role of k
D. Number of Model Layers
E. Robustness to Edge Perturbation
F. Graph Quality and Outcomes
V. DISCUSSION
VI. LIMITATONS OF THE STUDY
VII. FUTURE DIRECTIONS
VIII. CONCLUSION
REFERENCES

키워드

저자

• Kittikun Nimitsaengtian [ Faculty of Information Technology and Digital Innovaiton King Mongkut's University of Technology North Bangkok Bangkok, Thailand ]
• Maleerat Maliyaem [ Faculty of Information Technology and Digital Innovaiton King Mongkut's University of Technology North Bangkok Bangkok, Thailand ]
• Nalinpat Bhumpenpien [ Faculty of Information Technology and Digital Innovaiton King Mongkut's University of Technology North Bangkok Bangkok, Thailand ]
• Nathaporn Utakrit [ Faculty of Information Technology and Digital Innovaiton King Mongkut's University of Technology North Bangkok Bangkok, Thailand ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  한국차세대컴퓨팅학회 학술대회

• 간기

  반년간

• 수록기간

  2021~2025

• 십진분류

  KDC 566 DDC 004