No Cover Image

Journal article 227 views 43 downloads

Target unbiased meta-learning for graph classification

Ming Li, Shuo Zhu, Chunxu Li Orcid Logo, Wencang Zhao

Journal of Computational Design and Engineering, Volume: 8, Issue: 5, Pages: 1355 - 1366

Swansea University Author: Chunxu Li Orcid Logo

  • 66004.VoR.pdf

    PDF | Version of Record

    Copyright: The Author(s) 2021. . This is an Open Access article distributed under the terms of the Creative Commons Attribution License.

    Download (4.73MB)

Check full text

DOI (Published version): 10.1093/jcde/qwab050

Abstract

Even though numerous works focus on the few-shot learning issue by combining meta-learning, there are still limits to traditional graph classification problems. The antecedent algorithms directly extract features from the samples, and do not take into account the preference of the trained model to t...

Full description

Published in: Journal of Computational Design and Engineering
ISSN: 2288-5048
Published: Oxford University Press (OUP) 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa66004
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: Even though numerous works focus on the few-shot learning issue by combining meta-learning, there are still limits to traditional graph classification problems. The antecedent algorithms directly extract features from the samples, and do not take into account the preference of the trained model to the previously “seen” targets. In order to overcome the aforementioned issues, an effective strategy with training an unbiased meta-learning algorithm was developed in this paper, which sorted out problems of target preference and few-shot under the meta-learning paradigm. First, the interactive attention extraction module as a supplement to feature extraction was employed, which improved the separability of feature vectors, reduced the preference of the model for a certain target, and remarkably improved the generalization ability of the model on the new task. Second, the graph neural network was used to fully mine the relationship between samples to constitute graph structures and complete image classification tasks at a node level, which greatly enhanced the accuracy of classification. A series of experimental studies were conducted to validate the proposed methodology, where the few-shot and semisupervised learning problem has been effectively solved. It also proved that our model has better accuracy than traditional classification methods on real-world datasets.
Keywords: meta-learning, graph neural networks, graph classification, few-shot learning
College: Faculty of Science and Engineering
Issue: 5
Start Page: 1355
End Page: 1366