Multi-Class Imbalanced Graph Convolutional Network Learning
Multi-Class Imbalanced Graph Convolutional Network Learning
复制标题
DOI：
10.24963/ijcai.2020/398
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Min Shi;Yufei Tang;Xingquan Zhu;David A. Wilson;Jianxun Liu
中科院分区：
文献类型：
--
作者：
Min Shi;Yufei Tang;Xingquan Zhu;David A. Wilson;Jianxun Liu
网络数据通常在倾斜的类分布中表现出帕累托原则（即80/20规则），其中大多数顶点属于少数多数类，而少数类只包含少数实例。当类分布不平衡时，现有的图嵌入学习倾向于偏向多数类的节点，而少数类的节点训练不足。在本文中，我们提出了双正则化图卷积网络（DR-GCN）来处理多类不平衡图，其中施加了两种正则化来处理类不平衡表示学习。为了确保所有类都被平等地表示，我们提出了一个类条件对抗性训练过程，以促进标记节点的分离。同时，为了保持训练平衡（即保持所有类的拟合质量），我们通过最小化它们在嵌入空间中的差异，迫使未标记的节点遵循与标记节点相似的潜在分布。在现实世界的不平衡图上的实验表明，DR-GCN在节点分类、图聚类和可视化方面优于最先进的方法。
Networked data often demonstrate the Pareto principle (i.e., 80/20 rule) with skewed class distributions, where most vertices belong to a few majority classes and minority classes only contain a handful of instances. When presented with imbalanced class distributions, existing graph embedding learning tends to bias to nodes from majority classes, leaving nodes from minority classes under-trained. In this paper, we propose Dual-Regularized Graph Convolutional Networks (DR-GCN) to handle multi-class imbalanced graphs, where two types of regularization are imposed to tackle class imbalanced representation learning. To ensure that all classes are equally represented, we propose a class-conditioned adversarial training process to facilitate the separation of labeled nodes. Meanwhile, to maintain training equilibrium (i.e., retaining quality of fit across all classes), we force unlabeled nodes to follow a similar latent distribution to the labeled nodes by minimizing their difference in the embedding space. Experiments on real-world imbalanced graphs demonstrate that DR-GCN outperforms the state-of-the-art methods in node classification, graph clustering, and visualization.