NDGGNET-A Node Independent Gate based Graph Neural Networks

TL;DR

This paper introduces NDGGNET, a graph neural network framework that uses a node-degree based gate to dynamically adjust layer weights, enabling deeper models and improved performance on various graph tasks.

Contribution

The paper proposes a novel node-degree based gating mechanism that allows GNNs to deepen without over-smoothing, enhancing information aggregation for sparse and dense nodes.

Findings

Effective increase in model depth demonstrated

Improved accuracy on multiple datasets

Enhanced information propagation in GNNs

Abstract

Graph Neural Networks (GNNs) is an architecture for structural data, and has been adopted in a mass of tasks and achieved fabulous results, such as link prediction, node classification, graph classification and so on. Generally, for a certain node in a given graph, a traditional GNN layer can be regarded as an aggregation from one-hop neighbors, thus a set of stacked layers are able to fetch and update node status within multi-hops. For nodes with sparse connectivity, it is difficult to obtain enough information through a single GNN layer as not only there are only few nodes directly connected to them but also can not propagate the high-order neighbor information. However, as the number of layer increases, the GNN model is prone to over-smooth for nodes with the dense connectivity, which resulting in the decrease of accuracy. To tackle this issue, in this thesis, we define a novel framework that allows the normal GNN model to accommodate more layers. Specifically, a node-degree based gate is employed to adjust weight of layers dynamically, that try to enhance the information aggregation ability and reduce the probability of over-smoothing. Experimental results show that our proposed model can effectively increase the model depth and perform well on several datasets.