论文标题
超越图形神经网络中的同质性：当前的局限性和有效设计
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
论文作者
论文摘要
我们研究了在异质或低同质性的半监督节点分类任务中图形神经网络的表示能力，即在连接的节点可能具有不同类标签和不同特征的网络中。许多流行的GNN无法推广到此设置，甚至忽略图形结构的模型（例如，多层感知器）的模型甚至优于表现。在这种限制的驱动下，我们确定了一组关键设计 - 自我和邻居插入的分离，高阶邻域以及中间表示的组合 - 可以从异性下的图形结构中学习。我们将它们结合到图形神经网络H2GCN中，我们将其用作基础方法，以经验评估已识别设计的有效性。我们的经验分析超越了具有强大同质性的传统基准，表明，所鉴定的设计将GNN的准确性提高了40％和27％，而没有模型分别在具有异质性的合成和真实网络上，并在同质性的情况下产生了竞争性能。
We investigate the representation power of graph neural networks in the semi-supervised node classification task under heterophily or low homophily, i.e., in networks where connected nodes may have different class labels and dissimilar features. Many popular GNNs fail to generalize to this setting, and are even outperformed by models that ignore the graph structure (e.g., multilayer perceptrons). Motivated by this limitation, we identify a set of key designs -- ego- and neighbor-embedding separation, higher-order neighborhoods, and combination of intermediate representations -- that boost learning from the graph structure under heterophily. We combine them into a graph neural network, H2GCN, which we use as the base method to empirically evaluate the effectiveness of the identified designs. Going beyond the traditional benchmarks with strong homophily, our empirical analysis shows that the identified designs increase the accuracy of GNNs by up to 40% and 27% over models without them on synthetic and real networks with heterophily, respectively, and yield competitive performance under homophily.
