Scalable Graph Learning with Graph Convolutional Networks and Graph Attention Networks: Addressing Class Imbalance Through Augmentation and Optimized Hyperparameter Tuning

Uloženo v:
Podrobná bibliografie
Vydáno v:International Journal of Advanced Computer Science and Applications vol. 16, no. 7 (2025)
Hlavní autor: PDF
Vydáno:
Science and Information (SAI) Organization Limited
Témata:
On-line přístup:Citation/Abstract
Full Text - PDF
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

MARC

LEADER 00000nab a2200000uu 4500
001 3240918307
003 UK-CbPIL
022 |a 2158-107X 
022 |a 2156-5570 
024 7 |a 10.14569/IJACSA.2025.0160740  |2 doi 
035 |a 3240918307 
045 2 |b d20250101  |b d20251231 
100 1 |a PDF 
245 1 |a Scalable Graph Learning with Graph Convolutional Networks and Graph Attention Networks: Addressing Class Imbalance Through Augmentation and Optimized Hyperparameter Tuning 
260 |b Science and Information (SAI) Organization Limited  |c 2025 
513 |a Journal Article 
520 3 |a In this study, we propose a graph-based node classification to address challenges such as data scarcity, class imbalance, limited access to original textual content in benchmark datasets, semantic preservation, and model generalization in node classification tasks. Beyond simple data replication, we enhanced the Cora dataset by extracting content from its original PostScript files using a three-dimensional framework that combines in one pipeline NLP-based techniques such as PEGASUS paraphrase, synthetic model generation and a controlled subject aware synonym replacement. We substantially expanded the dataset to 17,780 nodes—representing an approximation of 6.57x scaling while maintaining semantic fidelity (WMD scores: 0.27-0.34). Our Bayesian Hyperparameter tuning was conducted using Optuna, along with k-fold cross-validation for a rigorous optimized model validation protocol. Our Graph Convolutional Network (GCN) model achieves 95.42% accuracy while Graph Attention Network (GAT) reaches 93.46%, even when scaled to a significantly larger dataset than the base. Our empirical analysis demonstrates that semantic-preserving augmentation helped us achieve better performance while maintaining model stability across scaled datasets, offering a cost-effective alternative to architectural complexity, making graph learning accessible to resource-constrained environments. 
653 |a Attention 
653 |a Datasets 
653 |a Semantics 
653 |a Tuning 
653 |a Classification 
653 |a Empirical analysis 
653 |a Machine learning 
653 |a Artificial neural networks 
653 |a Data replication 
653 |a Innovations 
653 |a Text categorization 
653 |a Computer science 
653 |a Neural networks 
653 |a Approximation 
653 |a Architecture 
653 |a Natural language processing 
773 0 |t International Journal of Advanced Computer Science and Applications  |g vol. 16, no. 7 (2025) 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3240918307/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3240918307/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch