论文标题
通过自适应光谱聚类对更高同质的重组图进行重组
Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering
论文作者
论文摘要
虽然越来越多的文献一直在研究在同粒细胞和异性图上都使用的新图形神经网络（GNN），但在将经典的GNN适应较低的杂物图上几乎没有做到。尽管限制了处理较低的动态图的能力，但经典的GNN仍然在效率，简单性和解释性等几种不错的特性中脱颖而出。在这项工作中，我们提出了一种新型的图形重组方法，可以将其集成到包括经典GNN在内的任何类型的GNN中，以利用现有GNN的好处，同时减轻其局限性。我们的贡献是三个方面：a）学习伪 - 元素向量的重量，以与已知的节点标签保持一致的适应性光谱聚类，b）提出一个新的密度感知的同型指标，该指标可与标签不平衡，c）基于适应性的谱系构成型号的量表，可以重建邻接的矩阵。实验结果表明，我们的图形重组方法可以显着提高六个经典GNN的性能，平均在较少的全体动态图上。增强性能与最新方法相媲美。
While a growing body of literature has been studying new Graph Neural Networks (GNNs) that work on both homophilic and heterophilic graphs, little has been done on adapting classical GNNs to less-homophilic graphs. Although the ability to handle less-homophilic graphs is restricted, classical GNNs still stand out in several nice properties such as efficiency, simplicity, and explainability. In this work, we propose a novel graph restructuring method that can be integrated into any type of GNNs, including classical GNNs, to leverage the benefits of existing GNNs while alleviating their limitations. Our contribution is threefold: a) learning the weight of pseudo-eigenvectors for an adaptive spectral clustering that aligns well with known node labels, b) proposing a new density-aware homophilic metric that is robust to label imbalance, and c) reconstructing the adjacency matrix based on the result of adaptive spectral clustering to maximize the homophilic scores. The experimental results show that our graph restructuring method can significantly boost the performance of six classical GNNs by an average of 25% on less-homophilic graphs. The boosted performance is comparable to state-of-the-art methods.
