Graph Attention Specialized Expert Fusion Model for Node Classification: Based on Cora and Pubmed Datasets
This work addresses class imbalance in graph node classification tasks, particularly for researchers working on citation networks like PubMed, but it is incremental as it builds on existing fusion and attention methods.
The paper tackles the problem of class-imbalanced node classification in graph neural networks, where certain categories show significantly lower accuracy, and proposes a Wasserstein-Rubinstein distance enhanced Expert Fusion Model (WR-EFM) that achieves balanced accuracies of 77.8%, 78.0%, and 79.9% across categories, improving the worst-performing category by 5.5% compared to traditional GCN.
Graph node classification is a fundamental task in graph neural networks (GNNs), aiming to assign predefined class labels to nodes. On the PubMed citation network dataset, we observe significant classification difficulty disparities, with Category 2 achieving only 74.4% accuracy in traditional GCN, 7.5% lower than Category 1. To address this, we propose a Wasserstein-Rubinstein (WR) distance enhanced Expert Fusion Model (WR-EFM), training specialized GNN models for Categories 0/1 (with layer normalization and residual connections) and Multi-hop Graph Attention Networks (GAT) for Category 2. The WR distance metric optimizes representation similarity between models, particularly focusing on improving Category 2 performance. Our adaptive fusion strategy dynamically weights models based on category-specific performance, with Category 2 assigned a GAT weight of 0.8. WR distance further guides the fusion process by measuring distributional differences between model representations, enabling more principled integration of complementary features. Experimental results show WR-EFM achieves balanced accuracy across categories: 77.8% (Category 0), 78.0% (Category 1), and 79.9% (Category 2), outperforming both single models and standard fusion approaches. The coefficient of variation (CV) of WR-EFM's category accuracies is 0.013, 77.6% lower than GCN's 0.058, demonstrating superior stability. Notably, WR-EFM improves Category 2 accuracy by 5.5% compared to GCN, verifying the effectiveness of WR-guided fusion in capturing complex structural patterns. This work provides a novel paradigm for handling class-imbalanced graph classification tasks. To promote the research community, we release our project at https://github.com/s010m00n/GASEM4NC.