Graph contrastive learning (GCL) emerges as the most representative approach
for graph representation learning, which leverages the principle of maximizing
mutual information (InfoMax) to learn node representations applied in
downstream tasks. To explore better generalization from GCL to downstream
tasks, previous methods heuristically define data augmentation or pretext
tasks. However, the generalization ability of GCL and its theoretical principle
are still less reported. In this paper, we first propose a metric named GCL-GE
for GCL generalization ability. Considering the intractability of the metric
due to the agnostic downstream task, we theoretically prove a mutual
information upper bound for it from an information-theoretic perspective.
Guided by the bound, we design a GCL framework named InfoAdv with enhanced
generalization ability, which jointly optimizes the generalization metric and
InfoMax to strike the right balance between pretext task fitting and the
generalization ability on downstream tasks. We empirically validate our
theoretical findings on a number of representative benchmarks, and experimental
results demonstrate that our model achieves state-of-the-art performance.

本文提出了一个名为 GCL-GE 的指标来衡量图对比学习 GCL 的一般化能力，并通过信息理论的角度理论上证明了一个互信息的上界。基于这个证明，我们设计了一个名为 InfoAdv 的 GCL 框架，该框架具有增强的一般化能力，在预训练任务适配和下游任务的一般化能力之间取得了平衡，并在各种基准测试中取得了最先进的性能。