arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.08690cs.LG
收藏

解决GNN的不平衡问题

Tackling the Imbalance for GNNs

National Center for Applied Mathematics, Tianjin University(天津大学应用数学中心)

Rui Wang, Weixuan Xiong, Qinghu Hou, Ou Wu

摘要:

与用于非图数据分类的深度神经网络不同,图神经网络(GNN)在表示节点时利用节点(或样本)之间的信息交换。在几乎所有现有的基准GNN数据集上,类别分布都显示出不平衡甚至高度倾斜的趋势。这种不均衡的分布会导致少数类中节点的误分类,甚至导致整个数据集的分类性能下降。首先,定义了一个节点级指标--标签差异指标($LDI$),定量分析了不平衡性与误分类之间的关系。类中的样本越少,其平均值$LDI$越高;样本的$LDI$越高,样本被错误分类的可能性越大。我们定义了一个新的损失,并提出了四个新的方法的基础上$LDI$。实验结果表明,我们提出的四种新方法中的三种方法的分类精度更好,在转导和归纳设置。$LDI$可以应用于其他GNN。

英文摘要:

Different from deep neural networks for non-graph data classification, graph neural networks (GNNs) leverage the information exchange between nodes (or samples) when representing nodes. The category distribution shows an imbalance or even a highly-skewed trend on nearly all existing benchmark GNN data sets. The imbalanced distribution will cause misclassification of nodes in the minority classes, and even cause the classification performance on the entire data set to decrease. This study explores the effects of the imbalance problem on the performances of GNNs and proposes new methodologies to solve it. First, a node-level index, namely, the label difference index ($LDI$), is defined to quantitatively analyze the relationship between imbalance and misclassification. The less samples in a class, the higher the value of its average $LDI$; the higher the $LDI$ of a sample, the more likely the sample will be misclassified. We define a new loss and propose four new methods based on $LDI$. Experimental results indicate that the classification accuracies of the three among our proposed four new methods are better in both transductive and inductive settings. The $LDI$ can be applied to other GNNs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑