论文标题
图形多项式卷积模型，用于非双性化图的节点分类
Graph Polynomial Convolution Models for Node Classification of Non-Homophilous Graphs
论文作者
论文摘要
我们研究了从高阶图卷积中的有效学习，并直接从邻接矩阵中学习以进行节点分类。我们重新访问缩放的图形残留网络，并从残留层中删除Relu激活，并在每个残留层上应用一个重量矩阵。我们表明，所得模型导致新的图卷积模型作为归一化邻接矩阵，残留权重矩阵和残差缩放参数的多项式。此外，我们提出了直接绘制多项式卷积模型和直接从邻接矩阵学习的自适应学习。此外，我们提出了完全自适应模型，以学习每个残留层的缩放参数。我们表明，所提出的方法的概括界限是特征值谱，缩放参数和剩余权重的上限的多项式。通过理论分析，我们认为所提出的模型可以通过限制卷积的更高范围并直接从邻接矩阵中学习来获得改进的概括界限。使用一系列的真实数据，我们证明了所提出的方法获得了提高的非全粒图淋巴结分类的精度。
We investigate efficient learning from higher-order graph convolution and learning directly from adjacency matrices for node classification. We revisit the scaled graph residual network and remove ReLU activation from residual layers and apply a single weight matrix at each residual layer. We show that the resulting model lead to new graph convolution models as a polynomial of the normalized adjacency matrix, the residual weight matrix, and the residual scaling parameter. Additionally, we propose adaptive learning between directly graph polynomial convolution models and learning directly from the adjacency matrix. Furthermore, we propose fully adaptive models to learn scaling parameters at each residual layer. We show that generalization bounds of proposed methods are bounded as a polynomial of eigenvalue spectrum, scaling parameters, and upper bounds of residual weights. By theoretical analysis, we argue that the proposed models can obtain improved generalization bounds by limiting the higher-orders of convolutions and direct learning from the adjacency matrix. Using a wide set of real-data, we demonstrate that the proposed methods obtain improved accuracy for node-classification of non-homophilous graphs.
