Hierarchical Graph Neural Networks for Few-Shot Learning

Page view(s)
82
Checked on Sep 24, 2023
Hierarchical Graph Neural Networks for Few-Shot Learning
Title:
Hierarchical Graph Neural Networks for Few-Shot Learning
Journal Title:
IEEE Transactions on Circuits and Systems for Video Technology
Publication Date:
09 February 2021
Citation:
Chen, C., Li, K., Wei, W., Zhou, J. T., & Zeng, Z. (2022). Hierarchical Graph Neural Networks for Few-Shot Learning. IEEE Transactions on Circuits and Systems for Video Technology, 32(1), 240–252. https://doi.org/10.1109/tcsvt.2021.3058098
Abstract:
Abstract—Recent graph neural network (GNN) based methods for few-shot learning (FSL) represent the samples of interest as a fully-connected graph and conduct reasoning on the nodes flatly, which ignores the hierarchical correlations among nodes. However, real-world categories may have hierarchical structures, and for FSL, it is important to extract the distinguishing features of the categories from individual samples. To explore this, we propose a novel hierarchical graph neural network (HGNN) for FSL, which consists of three parts, i.e., bottom-up reasoning, top-down reasoning, and skip connections, to enable the efficient learning of multi-level relationships. For the bottom-up reasoning, we design intra-class k-nearest neighbor pooling (intra-class knnPool) and inter-class knnPool layers, to conduct hierarchical learning for both the intra- and inter-class nodes. For the top-down reasoning, we propose to utilize graph unpooling (gUnpool) layers to restore the down-sampled graph into its original size. Skip connections are proposed to fuse multi-level features for the final node classification. The parameters of HGNN are learned by episodic training with the signal of node losses, which aims to train a well-generalizable model for recognizing unseen classes with few labeled data. Experimental results on benchmark datasets have demonstrated that HGNN outperforms other state-of-theart GNN based methods significantly, for both transductive and non-transductive FSL tasks. The dataset as well as the source code can be downloaded online
License type:
Publisher Copyright
Funding Info:
This work was partially funded by the National Key Research and Development Program of China under Grant 2019YFB2103004, in part by the National Natural Science Foundation of China under Grant 61902120, in part by the National Outstanding Youth Science Program of National Natural Science Foundation of China under Grant 61625202, in part by the International (Regional) Cooperation and Exchange Program of National Natural Science Foundation of China under Grant 61860206011, in part by the Postdoctoral Science Foundation of China under Grant 2019M662768 and Grant 2019TQ0086, and in part by the Natural Science Foundation of Hunan Province under Grant 2020JJ5083
Description:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
ISSN:
1558-2205
1051-8215
Files uploaded: