Scalable Graph Learning with Graph Convolutional Networks and Graph Attention Networks: Addressing Class Imbalance Through Augmentation and Optimized Hyperparameter Tuning
Uloženo v:
| Vydáno v: | International Journal of Advanced Computer Science and Applications vol. 16, no. 7 (2025) |
|---|---|
| Hlavní autor: | |
| Vydáno: |
Science and Information (SAI) Organization Limited
|
| Témata: | |
| On-line přístup: | Citation/Abstract Full Text - PDF |
| Tagy: |
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 |