High-Order Structure-Preserving Graph Neural Network for Few-Shot Learning
- 6 February 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (11) , 17987-18003
Abstract
Few-shot learning can find the latent structure information between the support and query data by the similarity metric of meta-learning to construct the discriminative model for recognizing the new categories with the less labeled samples. Most existing methods attempt to model the similarity relationships among samples within meta-tasks for achieving this goal. However, the relationship assessment among samples from distinct meta-tasks is challenging due to the differing metric relationships inherent to each respective meta-task. To address this issue, high-order structure preserving graph neural network (HOSP-GNN) can deeply explore the rich samples structure of the different meta-tasks to predict the label of the queried data based on the graph. HOSP-GNN can mine high-order structures to enhance their relevance by triple samples. In addition, it can also generate the updating rule of the different-order structures for node and edge representation optimization under manifold constraints. Notably, HOSP-GNN eliminates the need for retraining the learning model to recognize new classes, thanks to its high generalization of high-order structure that ensures model adaptability. The experiments demonstrate that HOSP-GNN outperforms state-of-the-art methods in four benchmark datasets, as well as on a self-built dataset focusing on endangered animals. The available code is https://github.com/yangfeifei02/HOSP.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61771386)
- Research and Development Program of Shaanxi (2020SF-359, 2021JQ-487)
This publication has 48 references indexed in Scilit:
- Few-shot image classification based on gradual machine learningExpert Systems with Applications, 2024
- EduCross: Dual adversarial bipartite hypergraph learning for cross-modal retrieval in multimodal educational slidesInformation Fusion, 2024
- Mutual Correlation Network for few-shot learningNeural Networks, 2024
- Edge-labeling based modified gated graph network for few-shot learningPattern Recognition, 2024
- High-order attentive graph neural network for session-based recommendationApplied Intelligence, 2022
- Efficient-PrototypicalNet with self knowledge distillation for few-shot learningNeurocomputing, 2021
- Deep graph learning for semi-supervised classificationPattern Recognition, 2021
- Relation-Guided Representation LearningNeural Networks, 2020
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Feature structure fusion and its applicationInformation Fusion, 2014