Graph neural networks (GNNs) have achieved superior performance in various
applications, but training dedicated GNNs can be costly for large-scale graphs.
Some recent work started to study the pre-training of GNNs. However, none of
them provide theoretical insights into the design of their frameworks, or clear
requirements and guarantees towards their transferability. In this work, we
establish a theoretically grounded and practically useful framework for the
transfer learning of GNNs. Firstly, we propose a novel view towards the
essential graph information and advocate the capturing of it as the goal of
transferable GNN training, which motivates the design of EGI (Ego-Graph
Information maximization) to analytically achieve this goal. Secondly, when
node features are structure-relevant, we conduct an analysis of EGI
transferability regarding the difference between the local graph Laplacians of
the source and target graphs. We conduct controlled synthetic experiments to
directly justify our theoretical conclusions. Comprehensive experiments on two
real-world network datasets show consistent results in the analyzed setting of
direct-transfering, while those on large-scale knowledge graphs show promising
results in the more practical setting of transfering with fine-tuning.

该研究提出了一种基于理论基础和实用性的 GNN 传递学习框架，首先提出了一种新颖的图信息视图，并提出通过 EGI (Ego-Graph Information maximization) 来分析实现传递学习目标，其次，当节点特征是结构相关的时，我们对 EGI 的可转移性进行了分析，综合两个真实数据集的实验结果表明具有传递性，在大规模知识图谱的转移学习中表现出良好的效果。