Information augmentation for few-shot node classification
Files
(Published version)
Date
2022
Authors
Wu, Z.
Zhou, P.
Wen, G.
Wan, Y.
Ma, J.
Cheng, D.
Zhu, X.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
IJCAI International Joint Conference on Artificial Intelligence, 2022, pp.3601-3607
Statement of Responsibility
Conference Name
31st International Joint Conference on Artificial Intelligence, IJCAI 2022 (23 Jul 2022 - 29 Jul 2022 : Vienna)
Abstract
Although meta-learning and metric learning have been widely applied for few-shot node classification (FSNC), some limitations still need to be addressed, such as expensive time costs for the meta-train and difficult of exploring the complex structure inherent the graph data. To address in issues, this paper proposes a new data augmentation method to conduct FSNC on the graph data including parameter initialization and parameter fine-tuning. Specifically, parameter initialization only conducts a multi-classification task on the base classes, resulting in good generalization ability and less time cost. Parameter fine-tuning is designed to have two data augmentation methods (i.e., support augmentation and shot augmentation) on the novel classes to generate sufficient node features so that any traditional supervised classifiers can be used to classify the query set. As a result, the proposed method is the first work of data augmentation for FSNC. Experiment results show the effectiveness and the efficiency of our proposed method, compared to state-of-the-art methods, in terms of different classification tasks.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright 2022 International Joint Conferences on Artificial Intelligence