Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View

Understand

Graph Neural Networks (GNNs) have achieved promising performance on a wide range of graph-based tasks.

• Despite their success, one severe limitation of GNNs is the over-smoothing issue (indistinguishable representations of nodes in different classes).
• In this work, we present a systematic and quantitative study on the over-smoothing issue of GNNs.
• First, we introduce two quantitative metrics, MAD and MADGap, to measure the smoothness and over-smoothness of the graph nodes representations, respectively.