Gradient Gating for Deep Multi-Rate Learning on Graphs

TL;DR

Gradient Gating (G$^2$) is a new framework that enhances deep GNNs by controlling message passing through multi-rate gating, addressing oversmoothing, and achieving state-of-the-art results on various graph tasks.

Contribution

The paper introduces Gradient Gating (G$^2$), a flexible framework that improves deep GNNs by mitigating oversmoothing through multi-rate gradient-based message passing.

Findings

G$^2$ alleviates oversmoothing in deep GNNs.

The framework achieves state-of-the-art performance on large-scale heterophilic graphs.

G$^2$ is compatible with any basic GNN layer.

Abstract

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.