When Do We Need GNN for Node Classification?

by   Sitao Luan, et al.

Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by additionally making use of graph structure based on the relational inductive bias (edge bias), rather than treating the nodes as collections of independent and identically distributed () samples. Though GNNs are believed to outperform basic NNs in real-world tasks, it is found that in some cases, GNNs have little performance gain or even underperform graph-agnostic NNs. To identify these cases, based on graph signal processing and statistical hypothesis testing, we propose two measures which analyze the cases in which the edge bias in features and labels does not provide advantages. Based on the measures, a threshold value can be given to predict the potential performance advantages of graph-aware models over graph-agnostic models.


page 1

page 2

page 3

page 4


Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?

Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using...

Edge Entropy as an Indicator of the Effectiveness of GNNs over CNNs for Node Classification

Graph neural networks (GNNs) extend convolutional neural networks (CNNs)...

Learning Visual Dynamics Models of Rigid Objects using Relational Inductive Biases

Endowing robots with human-like physical reasoning abilities remains cha...

Revisiting Heterophily For Graph Neural Networks

Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using...

Directed Acyclic Graph Neural Networks

Graph-structured data ubiquitously appears in science and engineering. G...

Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering

Graph neural networks (GNNs) based methods have achieved impressive perf...

Please sign up or login with your details

Forgot password? Click here to reset