论文标题
捕获基于图案的图形网络上的高阶结构
Capturing High-order Structures on Motif-based Graph Nerual Networks
论文作者
论文摘要
图形网络（GNN）是图形嵌入中的有效模型。它通过汇总邻居信息来学习不同节点的嵌入表示形式来提取浅色特征和邻里信息。但是，网络中许多节点的局部拓扑信息相似，浅层嵌入获得的网络表示易受结构噪声的网络，而低阶嵌入无法捕获高阶网络结构。另一方面，深层嵌入进行多层卷积。过滤器堆叠后，嵌入式分布被破坏，并进行图平滑。为了应对这些挑战，我们提出了一个新的框架，该框架利用网络图案从低级嵌入网络同质性和传播性下从低级嵌入网络学习网络的深度特征，然后将本地邻域信息与更深层的全球信息融合相结合，从而使节点的准确表示。在实际数据集上，我们的模型可以在链接预测和节点分类方面显着提高性能。
Graph Nerual Networks (GNNs) are effective models in graph embedding. It extracts shallow features and neighborhood information by aggregating neighbor information to learn the embedding representation of different nodes. However, the local topology information of many nodes in the network is similar, the network obtained by shallow embedding represents the network that is susceptible to structural noise, and the low-order embedding cannot capture the high-order network structure; on the other hand, the deep embedding undergoes multi-layer convolution. After the filters are stacked, the embedded distribution is destroyed, and graph smoothing occurs. To address these challenges, we propose a new framework that leverages network motifs to learn deep features of the network from low-level embeddings under the assumption of network homogeneity and transitivity, and then combines local neighborhood information with deeper global information fusion results in accurate representation of nodes. On real datasets, our model achieves significant performance improvement in link prediction and node classification.
