强传递关系与图神经网络
Strong Transitivity Relations and Graph Neural Networks
AI总结：
本研究提出TransGNN模型，通过区分并利用强传递关系与弱传递关系，将相似性概念从局部邻域扩展至全图，使图神经网络能同时捕获全局与局部相似性，在多个真实数据集的节点分类任务上显著提升了现有GNN模型性能。
摘要：
局部邻域在基于图的学习的嵌入生成中起着至关重要的作用。人们普遍认为，节点应当拥有与其邻居相似的嵌入表示。在本研究中，我们尝试谨慎地将相似性的概念从附近的邻域扩展到整个图。我们提供了一种基于传递关系的相似性扩展方法，这使得图神经网络（GNNs）能够在整个图上同时捕获全局相似性和局部相似性。我们引入了传递图神经网络（TransGNN），它超越了局部节点相似性，通过将强传递关系与弱传递关系区分开来并加以利用，从而考虑了全局相似性。我们在多个真实世界数据集上评估了我们的模型，结果表明，对于节点分类等任务，它显著提升了多种知名GNN模型的性能。
英文摘要：
Local neighborhoods play a crucial role in embedding generation in graph-based learning. It is commonly believed that nodes ought to have embeddings that resemble those of their neighbors. In this research, we try to carefully expand the concept of similarity from nearby neighborhoods to the entire graph. We provide an extension of similarity that is based on transitivity relations, which enables Graph Neural Networks (GNNs) to capture both global similarities and local similarities over the whole graph. We introduce Transitivity Graph Neural Network (TransGNN), which more than local node similarities, takes into account global similarities by distinguishing strong transitivity relations from weak ones and exploiting them. We evaluate our model over several real-world datasets and showed that it considerably improves the performance of several well-known GNN models, for tasks such as node classification.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
