Graph Attention Specialized Expert Fusion Model for Node Classification: Based on Cora and Pubmed Datasets

TL;DR

This paper introduces WR-EFM, a novel fusion model using Wasserstein-Rubinstein distance to improve node classification accuracy and stability across categories in graph neural networks, especially for challenging classes.

Contribution

The paper proposes a Wasserstein-Rubinstein distance enhanced fusion model that adaptively combines specialized GNNs for improved class-balanced node classification.

Findings

Achieves balanced accuracy of 79.9% on Category 2, outperforming single models.

Reduces coefficient of variation (CV) by 77.6%, indicating higher stability.

Improves Category 2 accuracy by 5.5% over traditional GCN.

Abstract

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.