Graph convolutional networks (GCNs) enable end-to-end learning on graph structured data. However, many works assume a given graph structure. When the input graph is noisy or unavailable, one approach is to construct or learn a latent graph structure. These methods typically fix the choice of node degree for the entire graph, which is suboptimal. Instead, we propose a novel end-to-end differentiable graph generator which builds graph topologies where each node selects both its neighborhood and its size. Our module can be readily integrated into existing pipelines involving graph convolution operations, replacing the predetermined or existing adjacency matrix with one that is learned, and optimized, as part of the general objective. As such it is applicable to any GCN. We integrate our module into trajectory prediction, point cloud classification and node classification pipelines resulting in improved accuracy over other structure-learning methods across a wide range of datasets and GCN backbones.

翻译：图卷积网络（GCNs）支持对图结构数据进行端到端学习。然而，许多研究假设图结构是给定的。当输入图存在噪声或不可用时，一种方法是构建或学习一个隐式图结构。这些方法通常为整个图固定节点度的选择，这并非最优方案。为此，我们提出了一种新颖的端到端可微图生成器，它能构建图拓扑结构，其中每个节点既可选择其邻域，也可选择其邻域大小。我们的模块可以轻松集成到现有的涉及图卷积操作的流水线中，用学习到的、作为总体目标一部分进行优化的邻接矩阵替换预定义或现有的邻接矩阵。因此，它适用于任何GCN。我们将该模块集成到轨迹预测、点云分类和节点分类流水线中，在多种数据集和GCN骨干网络上相比其他结构学习方法实现了更高的准确率。