论文标题
Glinkx：一个可扩展的统一框架，用于同粒和异质图
GLINKX: A Scalable Unified Framework For Homophilous and Heterophilous Graphs
论文作者
论文摘要
在图形学习中，关于图形启发的体系结构存在两个主要的归纳偏见：一方面，高阶相互作用和消息传递在同质图上很好地工作，并由GCN和GATS借用。但是，这样的体系结构无法轻易扩展到大型现实图形。另一方面，使用自我特征和邻接嵌入的浅（或节点级）模型在异性图中很好地工作。在这项工作中，我们提出了一种新型的可扩展浅方法 - glinkx-可以在同粒细胞和异质图上起作用。 Glinkx杠杆（i）新型的单个标签传播，（ii）自我/节点特征，（iii）知识图嵌入为位置嵌入，（iv）节点级训练和（v）低维信息传递。正式地，我们证明了新的误差界限并证明Glinkx的组成部分是合理的。在实验上，我们在几个同粒细胞和异质数据集上显示了它的有效性。
In graph learning, there have been two predominant inductive biases regarding graph-inspired architectures: On the one hand, higher-order interactions and message passing work well on homophilous graphs and are leveraged by GCNs and GATs. Such architectures, however, cannot easily scale to large real-world graphs. On the other hand, shallow (or node-level) models using ego features and adjacency embeddings work well in heterophilous graphs. In this work, we propose a novel scalable shallow method -- GLINKX -- that can work both on homophilous and heterophilous graphs. GLINKX leverages (i) novel monophilous label propagations, (ii) ego/node features, (iii) knowledge graph embeddings as positional embeddings, (iv) node-level training, and (v) low-dimensional message passing. Formally, we prove novel error bounds and justify the components of GLINKX. Experimentally, we show its effectiveness on several homophilous and heterophilous datasets.
