Should Graph Neural Networks Use Features, Edges, Or Both?

03/11/2021
by   Lukas Faber, et al.
0

Graph Neural Networks (GNNs) are the first choice for learning algorithms on graph data. GNNs promise to integrate (i) node features as well as (ii) edge information in an end-to-end learning algorithm. How does this promise work out practically? In this paper, we study to what extend GNNs are necessary to solve prominent graph classification problems. We find that for graph classification, a GNN is not more than the sum of its parts. We also find that, unlike features, predictions with an edge-only model do not always transfer to GNNs.

READ FULL TEXT
research
02/08/2020

Random Features Strengthen Graph Neural Networks

Graph neural networks (GNNs) are powerful machine learning models for va...
research
05/11/2019

Dissecting Graph Neural Networks on Graph Classification

Graph Neural Nets (GNNs) have received increasing attentions, partially ...
research
07/08/2020

Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditions

We present a systematic investigation using graph neural networks (GNNs)...
research
12/16/2020

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

Graph neural networks (GNNs) extend convolutional neural networks (CNNs)...
research
12/17/2022

Analyzing the Traffic of MANETs using Graph Neural Networks

Graph Neural Networks (GNNs) have been taking role in many areas, thanks...
research
07/24/2023

Learning Resource Allocation Policy: Vertex-GNN or Edge-GNN?

Graph neural networks (GNNs) update the hidden representations of vertic...
research
10/01/2020

Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking

Graph neural networks (GNNs) have become a popular approach to integrati...

Please sign up or login with your details

Forgot password? Click here to reset