We present Gradient Gating (G$^2$), a novel framework for improving the performance of Graph Neural Networks (GNNs). Our framework is based on gating the output of GNN layers with a mechanism for multi-rate flow of message passing information across nodes of the underlying graph. Local gradients are harnessed to further modulate message passing updates. Our framework flexibly allows one to use any basic GNN layer as a wrapper around which the multi-rate gradient gating mechanism is built. We rigorously prove that G$^2$ alleviates the oversmoothing problem and allows the design of deep GNNs. Empirical results are presented to demonstrate that the proposed framework achieves state-of-the-art performance on a variety of graph learning tasks, including on large-scale heterophilic graphs.

翻译：我们提出梯度门控（G$^2$），一种用于提升图神经网络（GNNs）性能的新型框架。该框架基于对GNN层输出施加门控机制，实现底层图中节点间消息传递信息的多速率流动。局部梯度被用来进一步调节消息传递更新。我们的框架灵活地允许将任意基础GNN层作为封装层，在其上构建多速率梯度门控机制。我们严格证明了G$^2$能够缓解过平滑问题，并支持设计深度GNN。实验结果表明，所提框架在多种图学习任务（包括大规模异配图）上均达到了最先进性能。