This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
AFGN: Adaptive Filtering Graph Neural Network for Few-Shot Learning
by
Qi Tan
Qi Tan 1,
Jialun Lai
Jialun Lai 1,
Chenrui Zhao
Chenrui Zhao 2,
Zongze Wu
Zongze Wu
Prof. Dr. Zongze Wu, a Distinguished Professor, PhD Supervisor, and the Dean of the College of and a [...]
Prof. Dr. Zongze Wu, a Distinguished Professor, PhD Supervisor, and the Dean of the College of Mechatronics and Control Engineering at Shenzhen University. He was a Professor at the School of Automation, Guangdong University of Technology from 2016 to 2022. He received a master's and doctor's degrees in control science and engineering from Xi'an Jiaotong University in 2002 and 2005, respectively. He has won a number of important awards, such as the Chinese Patent Silver Award, first-class Prize of the Ministry of Education’s Science and Technology Progress Award, second-class Prizes of the Ministry of Education’s Science and Technology Progress Award two times, and first-class prizes of Guangdong Province’s Science and Technology Award four times. His research interests include knowledge automation, machine vision and intelligent manufacturing.
1,3,* and
Xie Zhang
Xie Zhang 4,*
1
School of Automation, Guangdong University of Technology, Guangzhou 510006, China
2
College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China
3
College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, China
4
School of Electric Power Engineering, South China University of Technology, Guangzhou 510006, China
*
Authors to whom correspondence should be addressed.
Appl. Sci. 2024, 14(19), 8988; https://doi.org/10.3390/app14198988 (registering DOI)
Submission received: 12 August 2024
/
Revised: 27 September 2024
/
Accepted: 3 October 2024
/
Published: 5 October 2024
Abstract
The combination of few-shot learning and graph neural networks can effectively solve the issue of extracting more useful information from limited data. However, most graph-based few-shot models only consider the global feature information extracted by the backbone during the construction process, while ignoring the dependency information hidden within the features. Additionally, the essence of graph convolution is the filtering of graph signals, and the majority of graph-based few-shot models construct fixed, single-property filters to process these graph signals. Therefore, in this paper, we propose an Adaptive Filtering Graph Convolutional Neural Network (AFGN) for few-shot classification. AFGN explores the hidden dependency information within the features, providing a new approach for constructing graph tasks in few-shot scenarios. Furthermore, we design an adaptive filter for the graph convolution of AFGN, which can adaptively adjust its strategy for acquiring high and low-frequency information from graph signals based on different few-shot episodic tasks. We conducted experiments on three standard few-shot benchmarks, including image recognition and fine-grained categorization. The experimental results demonstrate that our AFGN performs better compared to other state-of-the-art models.
Share and Cite
MDPI and ACS Style
Tan, Q.; Lai, J.; Zhao, C.; Wu, Z.; Zhang, X.
AFGN: Adaptive Filtering Graph Neural Network for Few-Shot Learning. Appl. Sci. 2024, 14, 8988.
https://doi.org/10.3390/app14198988
AMA Style
Tan Q, Lai J, Zhao C, Wu Z, Zhang X.
AFGN: Adaptive Filtering Graph Neural Network for Few-Shot Learning. Applied Sciences. 2024; 14(19):8988.
https://doi.org/10.3390/app14198988
Chicago/Turabian Style
Tan, Qi, Jialun Lai, Chenrui Zhao, Zongze Wu, and Xie Zhang.
2024. "AFGN: Adaptive Filtering Graph Neural Network for Few-Shot Learning" Applied Sciences 14, no. 19: 8988.
https://doi.org/10.3390/app14198988
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.