Search for the UGLE Truth: An Investigation into Unsupervised GNN Learning Environments

05/10/2023
by   Will Leeney, et al.
0

Graph Neural Networks (GNNs) are a pertinent tool for any machine learning task due to their ability to learn functions over graph structures, a powerful and expressive data representation. The detection of communities, an unsupervised task has increasingly been performed with GNNs. Clustering nodes in a graph using the multi-dimensionality of node features with the connectivity of the graph has many applications to real world tasks from social networks to genomics. Unfortunately, there is currently a gap in the literature with no established sufficient benchmarking environment for fairly and rigorously evaluating GNN based community detection, thereby potentially impeding progress in this nascent field. We observe the particular difficulties in this setting is the ambiguous hyperparameter tuning environments combined with conflicting metrics of performance and evaluation datasets. In this work, we propose and evaluate frameworks for the consistent comparisons of community detection algorithms using GNNs. With this, we show the strong dependence of the performance to the experimental settings, exacerbated by factors such as the use of GNNs and the unsupervised nature of the task, providing clear motivation for the use of a framework to facilitate congruent research in the field.

READ FULL TEXT

page 1

page 9

page 10

research
11/28/2020

Self-Expressive Graph Neural Network for Unsupervised Community Detection

Graph neural networks are able to achieve promising performance on multi...
research
12/24/2022

Multi-duplicated Characterization of Graph Structures using Information Gain Ratio for Graph Neural Networks

Various graph neural networks (GNNs) have been proposed to solve node cl...
research
09/26/2019

Overlapping Community Detection with Graph Neural Networks

Community detection is a fundamental problem in machine learning. While ...
research
08/23/2023

Will More Expressive Graph Neural Networks do Better on Generative Tasks?

Graph generation poses a significant challenge as it involves predicting...
research
02/28/2022

GraphWorld: Fake Graphs Bring Real Insights for GNNs

Despite advances in the field of Graph Neural Networks (GNNs), only a sm...
research
03/02/2020

Benchmarking Graph Neural Networks

Graph neural networks (GNNs) have become the standard toolkit for analyz...
research
05/20/2019

Unsupervised Community Detection with Modularity-Based Attention Model

In this paper we take a problem of unsupervised nodes clustering on grap...

Please sign up or login with your details

Forgot password? Click here to reset