Multiple recent studies show a paradox in graph convolutional networks (GCNs), that is, shallow architectures limit the capability of learning information from high-order neighbors, while deep architectures suffer from over-smoothing or over-squashing. To enjoy the simplicity of shallow architectures and overcome their limits of neighborhood extension, in this work, we introduce Biaffine technique to improve the expressiveness of graph convolutional networks with a shallow architecture. The core design of our method is to learn direct dependency on long-distance neighbors for nodes, with which only one-hop message passing is capable of capturing rich information for node representation. Besides, we propose a multi-view contrastive learning method to exploit the representations learned from long-distance dependencies. Extensive experiments on nine graph benchmark datasets suggest that the shallow biaffine graph convolutional networks (BAGCN) significantly outperforms state-of-the-art GCNs (with deep or shallow architectures) on semi-supervised node classification. We further verify the effectiveness of biaffine design in node representation learning and the performance consistency on different sizes of training data.

翻译：多篇近期研究揭示了图卷积网络中的悖论：浅层结构限制了从高阶邻居学习信息的能力，而深层结构则面临过平滑或过压缩问题。为在保持浅层结构简洁性的同时克服其邻域扩展的限制，本研究引入双仿射技术提升浅层图卷积网络的表达能力。该方法的核心设计在于学习节点对远距离邻居的直接依赖关系，使得仅需单跳消息传递即可捕获用于节点表示的丰富信息。此外，我们提出多视角对比学习方法，以充分利用从长距离依赖中学到的表示。在九个图基准数据集上的大量实验表明，浅层双仿射图卷积网络在半监督节点分类任务上显著优于当前最先进的图卷积网络（无论深层或浅层架构）。我们进一步验证了双仿射设计在节点表示学习中的有效性，以及在不同训练数据规模下的性能稳定性。