Imbalanced graph classification with multi-scale oversampling graph neural networks
One main challenge in imbalanced graph classification is to learn expressive representations of the graphs in under-represented (minority) classes. Existing generic imbalanced learning methods, such as oversampling and imbalanced learning loss functions, can be adopted for enabling graph representat...
Saved in:
Main Authors: | , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9764 https://ink.library.smu.edu.sg/context/sis_research/article/10764/viewcontent/2405.04903v2.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-10764 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-107642024-12-16T02:43:21Z Imbalanced graph classification with multi-scale oversampling graph neural networks MA, Rongrong PANG, Guansong CHEN, Ling One main challenge in imbalanced graph classification is to learn expressive representations of the graphs in under-represented (minority) classes. Existing generic imbalanced learning methods, such as oversampling and imbalanced learning loss functions, can be adopted for enabling graph representation learning models to cope with this challenge. However, these methods often directly operate on the graph representations, ignoring rich discriminative information within the graphs and their interactions. To tackle this issue, we introduce a novel multi-scale oversampling graph neural network (MOSGNN) that learns expressive minority graph representations based on intra- and inter-graph semantics resulting from oversampled graphs at multiple scales - subgraph, graph, and pairwise graphs. It achieves this by jointly optimizing subgraph-level, graph-level, and pairwise-graph learning tasks to learn the discriminative information embedded within and between the minority graphs. Extensive experiments on 16 imbalanced graph datasets show that MOSGNN i) significantly outperforms five state-of-the-art models, and ii) offers a generic framework, in which different advanced imbalanced learning loss functions can be easily plugged in and obtain significantly improved classification performance. 2024-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9764 info:doi/10.1109/IJCNN60899.2024.10651097 https://ink.library.smu.edu.sg/context/sis_research/article/10764/viewcontent/2405.04903v2.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Graph classification Imbalanced learning Oversampling Graph neural networks Computer Sciences Graphics and Human Computer Interfaces |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Graph classification Imbalanced learning Oversampling Graph neural networks Computer Sciences Graphics and Human Computer Interfaces |
spellingShingle |
Graph classification Imbalanced learning Oversampling Graph neural networks Computer Sciences Graphics and Human Computer Interfaces MA, Rongrong PANG, Guansong CHEN, Ling Imbalanced graph classification with multi-scale oversampling graph neural networks |
description |
One main challenge in imbalanced graph classification is to learn expressive representations of the graphs in under-represented (minority) classes. Existing generic imbalanced learning methods, such as oversampling and imbalanced learning loss functions, can be adopted for enabling graph representation learning models to cope with this challenge. However, these methods often directly operate on the graph representations, ignoring rich discriminative information within the graphs and their interactions. To tackle this issue, we introduce a novel multi-scale oversampling graph neural network (MOSGNN) that learns expressive minority graph representations based on intra- and inter-graph semantics resulting from oversampled graphs at multiple scales - subgraph, graph, and pairwise graphs. It achieves this by jointly optimizing subgraph-level, graph-level, and pairwise-graph learning tasks to learn the discriminative information embedded within and between the minority graphs. Extensive experiments on 16 imbalanced graph datasets show that MOSGNN i) significantly outperforms five state-of-the-art models, and ii) offers a generic framework, in which different advanced imbalanced learning loss functions can be easily plugged in and obtain significantly improved classification performance. |
format |
text |
author |
MA, Rongrong PANG, Guansong CHEN, Ling |
author_facet |
MA, Rongrong PANG, Guansong CHEN, Ling |
author_sort |
MA, Rongrong |
title |
Imbalanced graph classification with multi-scale oversampling graph neural networks |
title_short |
Imbalanced graph classification with multi-scale oversampling graph neural networks |
title_full |
Imbalanced graph classification with multi-scale oversampling graph neural networks |
title_fullStr |
Imbalanced graph classification with multi-scale oversampling graph neural networks |
title_full_unstemmed |
Imbalanced graph classification with multi-scale oversampling graph neural networks |
title_sort |
imbalanced graph classification with multi-scale oversampling graph neural networks |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2024 |
url |
https://ink.library.smu.edu.sg/sis_research/9764 https://ink.library.smu.edu.sg/context/sis_research/article/10764/viewcontent/2405.04903v2.pdf |
_version_ |
1819113131828314112 |