论文标题
图形神经网络具有预先计算的节点特征
Graph Neural Networks with Precomputed Node Features
论文作者
论文摘要
大多数图形神经网络（GNN）无法区分某些图形或图中的某些节点。这使得无法解决某些分类任务。但是，在这些模型中添加其他节点功能可以解决此问题。我们介绍了几种这样的增强，包括（i）位置节点嵌入，（ii）规范节点ID和（iii）随机特征。这些扩展是由理论结果激励的，并通过对合成子图检测任务进行广泛测试来证实。我们发现，位置嵌入在这些任务中的其他扩展大大超过了其他扩展。此外，位置嵌入具有更好的样品效率，在不同的图形分布上表现良好，甚至在地面真实节点位置上表现出色。最后，我们表明，不同的增强功能在既定的GNN基准测试中都具有竞争力，并建议何时使用它们。
Most Graph Neural Networks (GNNs) cannot distinguish some graphs or indeed some pairs of nodes within a graph. This makes it impossible to solve certain classification tasks. However, adding additional node features to these models can resolve this problem. We introduce several such augmentations, including (i) positional node embeddings, (ii) canonical node IDs, and (iii) random features. These extensions are motivated by theoretical results and corroborated by extensive testing on synthetic subgraph detection tasks. We find that positional embeddings significantly outperform other extensions in these tasks. Moreover, positional embeddings have better sample efficiency, perform well on different graph distributions and even outperform learning with ground truth node positions. Finally, we show that the different augmentations perform competitively on established GNN benchmarks, and advise on when to use them.
