论文标题
HNHN：HyperGraph网络具有HyperEdge神经元
HNHN: Hypergraph Networks with Hyperedge Neurons
论文作者
论文摘要
HyperGraphs为许多现实世界数据集提供了自然的表示。我们提出了一个新颖的框架HNHN，以进行超图表的学习。 HNHN是一个超图卷积网络，具有非线性激活函数，均应用于超节点和高音，结合了标准化方案，可以灵活地调整高心脏性超息和高度顶点的重要性，并取决于数据集。与最先进的方法相比，我们证明了HNHN在现实世界数据集上的分类准确性和速度的提高。
Hypergraphs provide a natural representation for many real world datasets. We propose a novel framework, HNHN, for hypergraph representation learning. HNHN is a hypergraph convolution network with nonlinear activation functions applied to both hypernodes and hyperedges, combined with a normalization scheme that can flexibly adjust the importance of high-cardinality hyperedges and high-degree vertices depending on the dataset. We demonstrate improved performance of HNHN in both classification accuracy and speed on real world datasets when compared to state of the art methods.
