On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs

07/03/2021
by   Hejie Cui, et al.
Purdue University
Emory University
University of Illinois at Urbana-Champaign
0

Graph neural networks (GNNs) have been widely used in various graph-related problems such as node classification and graph classification, where the superior performance is mainly established when natural node features are available. However, it is not well understood how GNNs work without natural node features, especially regarding the various ways to construct artificial ones. In this paper, we point out the two types of artificial node features,i.e., positional and structural node features, and provide insights on why each of them is more appropriate for certain tasks,i.e., positional node classification, structural node classification, and graph classification. Extensive experimental results on 10 benchmark datasets validate our insights, thus leading to a practical guideline on the choices between different artificial node features for GNNs on non-attributed graphs. The code is available at https://github.com/zjzijielu/gnn-exp/.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/20/2019

On Node Features for Graph Neural Networks

Graph neural network (GNN) is a deep model for graph representation lear...
06/08/2020

Understanding Graph Neural Networks from Graph Signal Denoising Perspectives

Graph neural networks (GNNs) have attracted much attention because of th...
11/26/2022

Distribution Free Prediction Sets for Node Classification

Graph Neural Networks (GNNs) are able to achieve high classification acc...
08/16/2023

S-Mixup: Structural Mixup for Graph Neural Networks

Existing studies for applying the mixup technique on graphs mainly focus...
05/27/2022

Bayesian Robust Graph Contrastive Learning

Graph Neural Networks (GNNs) have been widely used to learn node represe...
11/08/2021

Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods

Graph Neural Networks (GNNs) have achieved state of the art performance ...
06/30/2023

Graphtester: Exploring Theoretical Boundaries of GNNs on Graph Datasets

Graph Neural Networks (GNNs) have emerged as a powerful tool for learnin...

Please sign up or login with your details

Forgot password? Click here to reset