A Variational Edge Partition Model for Supervised Graph Representation Learning
A Variational Edge Partition Model for Supervised Graph Representation Learning
复制标题
DOI：
--
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Yingying He;Chaojie Wang;Hao Zhang;Bo Chen;Mingyuan Zhou
中科院分区：
文献类型：
--
作者：
Yingying He;Chaojie Wang;Hao Zhang;Bo Chen;Mingyuan Zhou
图神经网络（GNN）通过边缘传播节点特征并学习如何在标签监督下转换聚合特征，在节点级和图级分类任务的监督特征提取方面取得了巨大成功。然而，GNN 通常将图结构视为给定的，而忽略边是如何形成的。本文介绍了一种图生成过程，用于模拟如何通过聚合一组重叠节点社区上的节点交互来生成观察到的边，每个社区通过逻辑 OR 机制对边做出贡献。基于这个生成模型，我们将每条边划分为多个特定于社区的加权边的总和，并使用它们来定义特定于社区的 GNN。提出了一个变分推理框架来共同学习一个基于 GNN 的推理网络，该网络将边缘划分为不同的社区、这些特定于社区的 GNN 以及一个基于 GNN 的预测器，该预测器结合了特定于社区的 GNN 以完成最终分类任务。对现实世界图数据集的广泛评估验证了所提出的方法在学习节点级和图级分类任务的判别表示方面的有效性。
Graph neural networks (GNNs), which propagate the node features through the edges and learn how to transform the aggregated features under label supervision, have achieved great success in supervised feature extraction for both node-level and graph-level classification tasks. However, GNNs typically treat the graph structure as given and ignore how the edges are formed. This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities, each of which contributes to the edges via a logical OR mechanism. Based on this generative model, we partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs. A variational inference framework is proposed to jointly learn a GNN-based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN-based predictor that combines community-specific GNNs for the end classification task. Extensive evaluations on real-world graph datasets have verified the effectiveness of the proposed method in learning discriminative representations for both node-level and graph-level classification tasks.