论文标题
二维WEISFEILER-LEHMAN图形神经网络用于链接预测
Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction
论文作者
论文摘要
链接预测是图神经网络（GNN）的一个重要应用。链接预测的大多数现有GNN基于一维Weisfeiler-Lehman（1-WL）测试。 1-wl-gnn首先通过迭代的相邻节点特征来计算中心，然后通过汇总成对节点表示来获得链接表示。正如先前的作品所指出的那样，这两步过程会导致较低的区分功能，因为自然要学习节点级表示，而不是链接级别。在本文中，我们研究了一种完全不同的方法，该方法可以基于\ textit {二维Weisfeiler-Lehman（2-WL）测试直接获得节点对（链接）表示。 2-WL测试直接使用链接（2个小说）作为消息传递单元而不是节点，因此可以直接获得链接表示。我们从理论上分析了2-WL检验的表达能力，以区分非同态链接，并证明其优越的链接与1-WL相比。基于不同的2-WL变体，我们提出了一系列用于链路预测的新型2-WL-GNN模型。在各种现实世界数据集上进行的实验证明了它们对最先进的基准的竞争性能，并且优于普通1-WL-GNN。
Link prediction is one important application of graph neural networks (GNNs). Most existing GNNs for link prediction are based on one-dimensional Weisfeiler-Lehman (1-WL) test. 1-WL-GNNs first compute node representations by iteratively passing neighboring node features to the center, and then obtain link representations by aggregating the pairwise node representations. As pointed out by previous works, this two-step procedure results in low discriminating power, as 1-WL-GNNs by nature learn node-level representations instead of link-level. In this paper, we study a completely different approach which can directly obtain node pair (link) representations based on \textit{two-dimensional Weisfeiler-Lehman (2-WL) tests}. 2-WL tests directly use links (2-tuples) as message passing units instead of nodes, and thus can directly obtain link representations. We theoretically analyze the expressive power of 2-WL tests to discriminate non-isomorphic links, and prove their superior link discriminating power than 1-WL. Based on different 2-WL variants, we propose a series of novel 2-WL-GNN models for link prediction. Experiments on a wide range of real-world datasets demonstrate their competitive performance to state-of-the-art baselines and superiority over plain 1-WL-GNNs.
