Graph neural networks (GNNs) continue to achieve state-of-the-art performance on many graph learning tasks, but rely on the assumption that a given graph is a sufficient approximation of the true neighborhood structure. In the presence of higher-order sequential dependencies, we show that the tendency of traditional graph representations to underfit each node's neighborhood causes existing GNNs to generalize poorly. To address this, we propose a novel Deep Graph Ensemble (DGE), which captures neighborhood variance by training an ensemble of GNNs on different neighborhood subspaces of the same node within a higher-order network structure. We show that DGE consistently outperforms existing GNNs on semisupervised and supervised tasks on four real-world data sets with known higher-order dependencies, even under a similar parameter budget. We demonstrate that learning diverse and accurate base classifiers is central to DGE's success, and discuss the implications of these findings for future work on GNNs.
翻译:图形神经网络(GNNs)继续在许多图表学习任务上取得最新业绩,但以某一图表足以接近真正的邻里结构为假设。在出现较高等级的相继依附关系的情况下,我们表明传统的图形显示方式往往对每个节点的邻里造成偏差,导致现有的GNNs没有很好地概括。为了解决这个问题,我们提议了一个新的深图组合(DGE),它通过在较高级别网络结构内同一节点的不同邻里小空间培训一组GNS,来捕捉社区差异。我们表明,DGE在四套已知较高等级依赖关系的真实世界数据集上,一直比现有的GNNS在半监督和监督下完成的任务要强,即便在类似的参数预算下也是如此。我们证明,学习多样化和准确的基础分类对DGE的成功至关重要,并讨论这些结论对GNes未来工作的影响。