论文标题
简化具有兼容标签传播的异性图上的节点分类
Simplifying Node Classification on Heterophilous Graphs with Compatible Label Propagation
论文作者
论文摘要
图形神经网络（GNN）主要用于图形学习任务。然而，最近的研究表明，众所周知的图算法，标签传播（LP）与浅神经网络相结合可以在高均高均高均值的图表上获得与GNN相当的性能。在本文中，我们表明，这种方法在低均匀性的图表上缺乏，其中节点通常连接到相反类的节点。为了克服这一点，我们仔细设计了基本预测因子与LP算法的组合，该算法享有封闭式解决方案以及收敛保证。我们的算法首先了解类兼容性矩阵，然后使用按类兼容性加权的LP算法汇总标签预测。在各种基准上，我们表明我们的方法在具有不同层次层次的图表上达到了领先的表现。同时，它的参数较少，需要更少的执行时间。经验评估表明，LP的简单适应性在同质和异性疾病方面的半监督节点分类中具有竞争力。
Graph Neural Networks (GNNs) have been predominant for graph learning tasks; however, recent studies showed that a well-known graph algorithm, Label Propagation (LP), combined with a shallow neural network can achieve comparable performance to GNNs in semi-supervised node classification on graphs with high homophily. In this paper, we show that this approach falls short on graphs with low homophily, where nodes often connect to the nodes of the opposite classes. To overcome this, we carefully design a combination of a base predictor with LP algorithm that enjoys a closed-form solution as well as convergence guarantees. Our algorithm first learns the class compatibility matrix and then aggregates label predictions using LP algorithm weighted by class compatibilities. On a wide variety of benchmarks, we show that our approach achieves the leading performance on graphs with various levels of homophily. Meanwhile, it has orders of magnitude fewer parameters and requires less execution time. Empirical evaluations demonstrate that simple adaptations of LP can be competitive in semi-supervised node classification in both homophily and heterophily regimes.
