论文标题
Clenshaw图神经网络
Clenshaw Graph Neural Networks
论文作者
论文摘要
图形卷积网络（GCN）使用带有消息的范式范围的范围范围的范围，是学习图表表示的基础方法。最近的GCN模型使用各种残差连接技术来减轻模型降解问题，例如过度平滑和梯度消失。但是，现有的残差连接技术无法像图形光谱域那样广泛使用基础图结构，这对于在异性图上获得令人满意的结果至关重要。在本文中，我们介绍了使用Clenshaw求和算法来增强GCN模型的表现力的GNN模型Clenshawgcn。 Clenshawgcn将标准GCN模型与两个直接的残差模块相对，即自适应初始残留连接和负二阶残留连接。我们表明，通过添加这两个残差模块，Clenshawgcn在Chebyshev下隐式模拟多项式滤波器，至少具有与多项式光谱GNN一样多的表达能力。此外，我们进行了全面的实验，以证明模型比空间和光谱GNN模型的优越性。
Graph Convolutional Networks (GCNs), which use a message-passing paradigm with stacked convolution layers, are foundational methods for learning graph representations. Recent GCN models use various residual connection techniques to alleviate the model degradation problem such as over-smoothing and gradient vanishing. Existing residual connection techniques, however, fail to make extensive use of underlying graph structure as in the graph spectral domain, which is critical for obtaining satisfactory results on heterophilic graphs. In this paper, we introduce ClenshawGCN, a GNN model that employs the Clenshaw Summation Algorithm to enhance the expressiveness of the GCN model. ClenshawGCN equips the standard GCN model with two straightforward residual modules: the adaptive initial residual connection and the negative second-order residual connection. We show that by adding these two residual modules, ClenshawGCN implicitly simulates a polynomial filter under the Chebyshev basis, giving it at least as much expressive power as polynomial spectral GNNs. In addition, we conduct comprehensive experiments to demonstrate the superiority of our model over spatial and spectral GNN models.
