论文标题
我们什么时候需要图形神经网络进行节点分类？
When Do We Need Graph Neural Networks for Node Classification?
论文作者
论文摘要
图形神经网络（GNN）通过基于关系电感偏置（边缘偏置）的图形结构来扩展基本神经网络（NNS），而不是将节点作为独立和相同分布的（I.I.I.D.）样本的集合。尽管据信GNN在现实世界任务中的表现要优于基本NN，但发现在某些情况下，GNN的性能增益很小，甚至表现不佳的Graph-Nostic NNS。为了根据图形信号处理和统计假设检验来识别这些情况，我们提出了两项措施，分析了特征和标签中边缘偏置不提供优势的情况。基于衡量标准，可以给出一个阈值，以预测图形感知模型的潜在性能优势而不是图形模型。
Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by additionally making use of graph structure based on the relational inductive bias (edge bias), rather than treating the nodes as collections of independent and identically distributed (i.i.d.) samples. Though GNNs are believed to outperform basic NNs in real-world tasks, it is found that in some cases, GNNs have little performance gain or even underperform graph-agnostic NNs. To identify these cases, based on graph signal processing and statistical hypothesis testing, we propose two measures which analyze the cases in which the edge bias in features and labels does not provide advantages. Based on the measures, a threshold value can be given to predict the potential performance advantages of graph-aware models over graph-agnostic models.
