Graph Neural Networks (GNNs), originally proposed for node classification, have also motivated many recent works on edge prediction (a.k.a., link prediction). However, existing methods lack elaborate design regarding the distinctions between two tasks that have been frequently overlooked: (i) edges only constitute the topology in the node classification task but can be used as both the topology and the supervisions (i.e., labels) in the edge prediction task; (ii) the node classification makes prediction over each individual node, while the edge prediction is determinated by each pair of nodes. To this end, we propose a novel edge prediction paradigm named Edge-aware Message PassIng neuRal nEtworks (EMPIRE). Concretely, we first introduce an edge splitting technique to specify use of each edge where each edge is solely used as either the topology or the supervision (named as topology edge or supervision edge). We then develop a new message passing mechanism that generates the messages to source nodes (through topology edges) being aware of target nodes (through supervision edges). In order to emphasize the differences between pairs connected by supervision edges and pairs unconnected, we further weight the messages to highlight the relative ones that can reflect the differences. In addition, we design a novel negative node-pair sampling trick that efficiently samples 'hard' negative instances in the supervision instances, and can significantly improve the performance. Experimental results verify that the proposed method can significantly outperform existing state-of-the-art models regarding the edge prediction task on multiple homogeneous and heterogeneous graph datasets.

翻译：图神经网络（GNN）最初被提出用于节点分类，也推动了许多近来关于边预测（亦称链接预测）的研究工作。然而，现有方法缺乏对这两类任务之间常被忽视的差异的精细设计：(i)在节点分类任务中，边仅构成拓扑结构，但在边预测任务中，边既可作为拓扑结构，也可作为监督信号（即标签）；(ii)节点分类是对每个节点进行预测，而边预测则取决于每对节点。为此，我们提出了一种新颖的边预测范式，名为边感知消息传递神经网络（EMPIRE）。具体而言，我们首先引入一种边分割技术来指定每条边的用途，其中每条边仅用作拓扑结构或监督信号（分别称为拓扑边或监督边）。接着，我们开发了一种新的消息传递机制，该机制通过拓扑边生成消息至源节点，同时感知通过监督边的目标节点。为了强调由监督边连接的节点对与未连接节点对之间的差异，我们进一步对消息进行加权，以突出能够反映这些差异的相对消息。此外，我们设计了一种新颖的负节点对采样技巧，该技巧能高效地从监督实例中采样"困难"负实例，并显著提升性能。实验结果表明，在多个同构和异构图数据集上的边预测任务中，所提方法能显著优于现有最先进模型。