AM-HGCN: An Adaptive Multi-Head Hypergraph Convolutional Network for Few-Shot Regression

NAVIGATE

Table of Contents

STATISTICS

Viewed5

Downloads17

AM-HGCN: An Adaptive Multi-Head Hypergraph Convolutional Network for Few-Shot Regression

PDF下载 (17)

[1]WangMei,YAN Zujia,GAO Yatian,et al.AM-HGCN: An Adaptive Multi-Head Hypergraph Convolutional Network for Few-Shot Regression[J].Journal of Zhengzhou University (Engineering Science),2027,48(XX):1-8.[doi:10.13705/j. issn.1671-6833.2026.02.003]

Copy

Journal of Zhengzhou University (Engineering Science)[ISSN 1671-6833/CN 41-1339/T] Volume: 48 Number of periods: 2027 XX Page number: 1-8 Column: Public date: 2027-12-10

Title:: AM-HGCN: An Adaptive Multi-Head Hypergraph Convolutional Network for Few-Shot Regression

Author(s):: WangMei ^1,2 , YAN Zujia ^1,2 , GAO Yatian ^1,2 , GAO Juntao^1,2; 1. Heilongjiang Key Laboratory of Petroleum Big Data and Intelligent Analysis, Daqing 163318, China; 2. School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, China

Keywords:: Few- Shot Learning; Hypergraph; Hypergraph Convolutional Neural Network; Multi head attention mechanism; Meta le

CLC:: TP301. 6O 1-0

DOI:: 10.13705/j. issn.1671-6833.2026.02.003

Abstract:: High-order interactions among multiple nodes were difficult to be captured by graph neural networks based on binary-edge structures, and static graph topologies were unable to adapt to dynamic data distributions. To address these limitations, a few-shot regression model based on adaptive multi-head hypergraph convolutional networks (AM-HGCN) was proposed, in which feature similarity and topological structure were integrated through a dynamic hypergraph construction method, multi-scale hyperedges were generated using k-hop neighbors and k-nearest neighbors (k-NN) strategies to enable adaptive capture of feature interactions, a multi-head hypergraph convolutional network was designed to extract heterogeneous features via parallel attention heads and fuse multi-granularity information through a dynamic gating mechanism to enhance expressive capability, and a model-agnostic meta-learning framework was introduced to achieve rapid task adaptation through inner- and outer-loop optimization. Experiments were conducted on the Boston Housing, Energy Efficiency, IMDB, and MiniImageNet datasets, and for structured datasets, AM-HGCN was observed to outperform mainstream baseline models significantly in evaluation metrics, with the coefficient of determination (R^2) improved by up to 1.1%, validating the model’s effectiveness in capturing complex relationships. Significance tests yielded a p-value of 0.04, statistically confirming the reliability of this improvement, and ablation studies further demonstrated that the collaborative effect of dynamic hypergraphs and multi-head attention mechanisms was crucial for the enhancement of few-shot regression performance, overall validating the effectiveness of the proposed method.

References:: [1] Zhao Kailin, Jin Xiaolong, Wang Yuanzhuo. Survey on few-shot learning [J]. Journal of Software, 2021, 32(2): 349-369. [赵凯林, 靳小龙, 王元卓. 小样本学习研究综述 [J]. 软件学报, 2021, 32(2): 349-369.]
[2] Wang Benben, Yan Yuefei, Hu Huizhen, et al. A predictive approach for cerebral small vessel disease based on imbalanced limited-sample data [J]. Electro-Mechanical Engineering, 2025, 41(3): 87-92. [王奔, 严粤飞, 胡慧珍, 等. 基于小样本不平衡数据的脑血管病预测方法 [J]. 电子机械工程, 2025, 41(3): 87-92.]
[3] Zhou Wei, Wei Mingan, Xu Haixia, et al. A few-shot land cover classification model for remote sensing images based on multimodality [J]. Journal of Electronics & Information Technology, 2025, 47(6): 1747-1761. [周维, 魏名安, 许海霞, 等. 基于多模态的小样本遥感影像地物分类模型 [J]. 电子与信息学报, 2025, 47(6): 1747-1761.]
[4] Gidaris S, Komodakis N. Generating classification weights with GNN denoising autoencoders for few-shot learning [C] // Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2019: 21-30.
[5] Velickovic, P., Cucurull, G., Casanova, A., et al. Graph attention networks [PP/OL]. [PP/OL]. V1. ArXiv3 (2017-10-30) [2028-02-04]. https://doi.org/10.48550/arXiv.1710.10903.
[6] Zhao Xiao, (Yuan/Yun) Xiaosa, Liu Ruiling, et al. Small sample plant image classification based on wavelet multi-frequency feature fusion enhancement [J/OL]. Computer Engineering and Applications, 2025-05-21. https://link.cnki.net/urlid/11.2127.tp.20250520.1517.003. [赵晓, 负潇洒, 刘睿玲, 等. 基于小波多频特征融合增强的小样本植物图像分类 [J/OL]. 计算机工程与应用, 2025-05-21. https://link.cnki.net/urlid/11.2127.tp.20250520.1517.003.]
[7] Ge Xiaoshan, Zheng Mengmeng. Study on classification of few-shot remote sensing images based on SER-GNN [J]. Journal of Henan Polytechnic University (Natural Science), 2025, 44(5): 144-151. [葛小三, 郑猛. 基于SER-GNN的小样本遥感影像分类研究 [J]. 河南理工大学学报(自然科学版), 2025, 44(5): 144-151.]
[8] Shen Yu, Wang Ruoxuan, Li Jiangcheng, et al. A Small-Sample Time Series Prediction Model Based on Graph Structure [J/OL]. Journal of Beihang University, 1-14 [2025-07-29]. https://doi.org/10.13700/j.bh.1001-5965.2025.0198. [沈瑜, 王若瑄, 李江程, 等. 基于图结构的小样本时间序列预测模型 [J/OL]. 北京航空航天大学学报, 1-14 [2025-07-29]. https://doi.org/10.13700/j.bh.1001-5965.2025.0198.]
[9] Liang Zhuomin, Bai Liang, Yang Xian, et al. Multi-channel disentangled graph neural networks with different types of self-constraints [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, 47(9): 8001-8012.
[10] Berge, C. Hypergraphs: combinatorics of finite sets [M]. New York: Elsevier Science & Technology Books, 1984.
[11] Feng Yifan, Huaxuan, Zhang Zixhao, et al. Hypergraph neural networks [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 3558-3565.
[12] Bai Song, Zhang Feihu, Torr P H S. Hypergraph convolution and hypergraph attention [J]. Pattern Recognition, 2021, 110: 107637.
[13] Wu Yue, Wang Ying, Wang Xin, et al. Motif-based hypergraph convolution for semi-supervised node classification on heterogeneous graph [J]. Chinese Journal of Computers, 2021, 44(11): 2248-2260. [吴越, 王英, 王鑫, 等. 基于超图卷积的异质网络半监督节点分类 [J]. 计算机学报, 2021, 44(11): 2248-2260.]
[14] Jiang Jianwen, Wei Yuxuan, Feng Yifan, et al. Dynamic hypergraph neural networks [C] // Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization, 2019: 2635-2641.
[15] Feng Yifan, Huaxuan, Zhang Zixhao, et al. Hypergraph neural networks [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 3558-3565.
[16] Harrison D, Rubinfeld D L. Hedonic housing prices and the demand for clean air [J]. Journal of Environmental Economics and Management, 1978, 5(1): 81-102.
[17] Chen Jiandong, Liu Jialu, Qi Jie, et al. City- and county-level spatio-temporal energy consumption and efficiency datasets for China from 1997 to 2017 [J]. Scientific Data, 2022, 9: 101.
[18] Zhai Mengxin, Zhou Yanling, Yu Hang. Few-shot text classification based on question-oriented prompt-tuning [J]. Application Research of Computers, 2025, 42(3): 708-713. [翟梦鑫, 周艳玲, 余杭. 基于问题导向提示调优小样本文本分类 [J]. 计算机应用研究, 2025, 42(3): 708-713.]
[19] Zhou Bin, Xiao Hao, Qin Yijia, et al. Local prototype small sample classification model integrating mixed attention mechanism [J/OL]. Journal of Frontiers of Computer Science and Technology, 2025-03-11. https://kns.cnki.net/kcms/detail/11.5602.TP.20250311.1049.002.html. [周彬, 鲜浩, 秦艺嘉, 等. 融合混合注意力机制的局部原型小样本分类模型 [J/OL]. 计算机科学与探索, 2025-03-11. https://kns.cnki.net/kcms/detail/11.5602.TP.20250311.1049.002.html.]
[20] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks [PP/OL]. V4. ArXiv (2017-02-22) [--]. https://doi.org/10.48550/arXiv.1609.02907.
[21] Li Peiwen, Li Feijiang, Wang Jieting, et al. Clustering method for tabular data based on pretrained foundation models with synthetic data [J/OL]. Journal of Computer Research and Development, https://link.cnki.net/urlid/11.1777.TP.20250723.1002.004. [李培文, 李飞江, 王婕婷, 等. 基于合成数据预训练基础模型的表格数据聚类方法 [J/OL]. 计算机研究与发展, https://link.cnki.net/urlid/11.1777.TP.20250723.1002.004.]

Similar References:

Memo

Last Update: 2026-04-03