Multi-Graph Learning Based on Structure-Aware

FU Dong-lai; GAO Ze-an

doi:10.12263/DZXB.20230565

您当前的位置：

首页 >

文章列表页 >

Multi-Graph Learning Based on Structure-Aware

PAPERS | 更新时间：2025-12-24

- Multi-Graph Learning Based on Structure-Aware
- ACTA ELECTRONICA SINICA Vol. 52, Issue 7, Pages: 2407-2417(2024)
- 作者机构：
  
  中北大学软件学院，山西太原 030051
- 作者简介：
- 基金信息：
- DOI：10.12263/DZXB.20230565
  CLC： TP319;TP391.4
- Received：16 June 2023，
  
  Revised：2024-03-28，
  
  Published：25 July 2024
- 稿件说明：
移动端阅览
付东来, 高泽安. 基于结构感知的多图学习方法[J]. 电子学报, 2024, 52(07): 2407-2417.

FU Dong-lai, GAO Ze-an. Multi-Graph Learning Based on Structure-Aware[J]. Acta Electronica Sinica, 2024, 52(07): 2407-2417.
付东来, 高泽安. 基于结构感知的多图学习方法[J]. 电子学报, 2024, 52(07): 2407-2417. DOI：10.12263/DZXB.20230565

FU Dong-lai, GAO Ze-an. Multi-Graph Learning Based on Structure-Aware[J]. Acta Electronica Sinica, 2024, 52(07): 2407-2417. DOI：10.12263/DZXB.20230565

摘要

多图学习是一种非常重要的学习范式.与多示例学习相比，在多图学习中包表示一个对象，包中的每一个图对应一个子对象.这种数据表示方法能够表达子对象的结构信息.但是，现有的多图学习方法不仅隐含假设包内的图满足独立同分布，而且多采用将多图学习问题转变为多示例学习问题的技术思路.这类多图学习方法容易损失图自身及图间的结构信息.针对上述问题，本文提出一种基于结构感知的多图学习方法，有效学习图自身和图间的结构信息.该方法利用图核，通过计算图之间的相似度保留图自身的结构信息，通过生成包级图表达图间的结构信息，并且设计包编码器有效学习图间的结构信息.在NCI（1）、NCI（109）和AIDB三个多图数据集上的实验结果表明，所提方法相较于现有方法在准确率、精确率、

值和AUC上分别平均提高了5.97%、3.44%、4.48%和2.56%，在召回率上平均降低了2.12%.

Abstract

Multi-graph learning is a very important learning paradigm. Compared with multi-instance learning

in multi-graph learning

a bag represents an object

and each graph in the bag corresponds to a sub-object. This data representation method can express the structural inform

ation of sub-objects. However

existing multi-graph learning methods not only implicitly assume that the graphs in the bag satisfy independent and identical distribution

but also mostly adopt the technical idea of transforming multi-graph learning problems into multi-instance learning problems. This type of multi-graph learning method easily loses the structural information of the graph itself and the relationships between graphs. In response to the above problems

a multi-graph learning method based on structure awareness is proposed to effectively learn the structural information of the graph itself and the relationships between graphs. This method uses graph kernels to retain the structural information of the graph itself by calculating the similarity between graphs

expresses the structural information between graphs by generating bag-level graphs

and designs a bag encoder to effectively learn the structural information between graphs. Experimental results on the NCI(1)

NCI(109)

and AIDB datasets show that compared with existing methods

the proposed method improved by 5.97%

3.44%

4.48%

and 2.56% in accuracy

precision

value

and AUC respectively. In terms of recall rate decreased by 2.12%.

关键词

Keywords

references

朱越 , 姜远 , 周志华 . 一种基于多示例多标记学习的新标记学习方法 [J ] . 中国科学: 信息科学 , 2018 , 48 ( 12 ): 1670 - 1680 .

ZHU Y , JIANG Y , ZHOU Z H . Multi-instance multi-label new label learning [J ] . Scientia Sinica (Informationis) , 2018 , 48 ( 12 ): 1670 - 1680 . (in Chinese)

YANG Y , TU Y L , LEI H C , et al . HAMIL: Hierarchical aggregation-based multi-instance learning for microscopy image classification [J ] . Pattern Recognition , 2023 , 136 : 109245 .

包翔 , 刘桂锋 , 崔靖华 . 多示例多标签学习在中文专利自动分类中的应用研究 [J ] . 图书情报工作 , 2021 , 65 ( 8 ): 107 - 113 .

BAO X , LIU G F , CUI J H . Application of multi instance multi label learning in Chinese patent automatic classification [J ] . Library and Information Service , 2021 , 65 ( 8 ): 107 - 113 . (in Chinese)

WANG C , WU Y , WANG C , et al . Attention-based multiple-instance learning for Pediatric bone age assessment with efficient and interpretable [J ] . Biomedical Signal Processing and Control , 2023 , 79 : 104028 .

ZHANG D K , YIN J , ZHU X Q , et al . Network representation learning: A survey [J ] . IEEE Transactions on Big Data , 2020 , 6 ( 1 ): 3 - 28 .

ZHAO Y H , WANG Y J , WANG Z K , et al . Multi-graph multi-label learning with dual-granularity labeling [C ] // Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining . New York : ACM , 2021 : 2327 - 2337 .

WANG M X , ZHAO Y H , WANG Y J , et al . Image emotion multi-label classification based on multi-graph learning [J ] . Expert Systems with Applications , 2023 , 231 : 120641 .

赵宇海 , 何子豪 , 谢儒 , 等 . 一种基于双模态的药物靶标多标签分类方法 : CN116469484A [P ] . 2023-07-21 .

DIETTERICH T G , LATHROP R H , LOZANO-PÉREZ T . Solving the multiple instance problem with axis-parallel rectangles [J ] . Artificial Intelligence , 1997 , 89 ( 1/2 ): 31 - 71 .

TANG P , WANG X G , BAI X , et al . Multiple instance detection network with online instance classifier refinement [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 3059 - 3067 .

ANGELIDIS S , LAPATA M . Multiple instance learning networks for fine-grained sentiment analysis [J ] . Transactions of the Association for Computational Linguistics , 2018 , 6 : 17 - 31 .

LIU M X , ZHANG J , ADELI E , et al . Landmark-based deep multi-instance learning for brain disease diagnosis‍ [J ] . Medical Image Analysis , 2018 , 43 : 157 - 168 .

WANG Y , LI J C , METZE F . A comparison of five multiple instance learning pooling functions for sound event detection with weak labeling [C ] // 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Piscataway : IEEE , 2019 : 31 - 35 .

LIU X , JIAO L C , ZHAO J Q , et al . Deep multiple instance learning-based spatial-spectral classification for PAN and MS imagery [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2018 , 56 ( 1 ): 461 - 473 .

赵璐 , 袁立明 , 郝琨 . 多示例学习算法综述 [J ] . 计算机科学 , 2022 , 49 ( S1 ): 93 - 99 .

ZHAO L , YUAN L M , HAO K . Review of multi-instance learning algorithms [J ] . Computer Science , 2022 , 49 ( S1 ): 93 - 99 . (in Chinese)

ZHANG Q , GOLDMAN S A . EM-DD: An improved multiple-instance learning technique [C ] // Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic . New York : ACM , 2001 : 1073 - 1080 .

ANDREWS S , TSOCHANTARIDIS I , HOFMANN T . Support vector machines for multiple-instance learning‍ [C ] // Proceedings of the 15th International Conference on Neural Information Processing Systems . New York : ACM , 2002 : 577 - 584 .

CHEN Y X , BI J B , WANG J Z . MILES: Multiple-instance learning via embedded instance selection [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2006 , 28 ( 12 ): 1931 - 1947 .

WANG J , ZUCKER J D . Solving the multiple-instance problem: A lazy learning approach [C ] // Proceedings of the Seventeenth International Conference on Machine Learning . New York : ACM , 2000 : 1119 - 1126 .

AMORES J . Multiple instance classification: Review, taxonomy and comparative study [J ] . Artificial Intelligence , 2013 , 201 : 81 - 105 .

ZHOU Z H , ZHANG M L . Solving multi-instance problems with classifier ensemble based on constructive clustering [J ] . Knowledge and Information Systems , 2007 , 11 ( 2 ): 155 - 170 .

CHEPLYGINA V , TAX D M J , LOOG M . Multiple instance learning with bag dissimilarities [J ] . Pattern Recognition , 2015 , 48 ( 1 ): 264 - 275 .

WANG X G , YAN Y L , TANG P , et al . Revisiting multiple instance neural networks [J ] . Pattern Recognition , 2018 , 74 ( C ): 15 - 24 .

ILSE M , TOMCZAK J M , WELLING M . Attention-based deep multiple instance learning [EB/OL ] . ( 2018 )[2023 ] . http://arxiv.org/abs/1802.04712 http://arxiv.org/abs/1802.04712 .

PAL S , VALKANAS A , REGOL F , et al . Bag graph: Multiple instance learning using Bayesian graph neural networks [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2022 , 36 ( 7 ): 7922 - 7930 .

ZHAO P J , LIAO W J , HUANG Y L , et al . Intelligent design of shear wall layout based on graph neural networks‍ [J ] . Advanced Engineering Informatics , 2023 , 55 : 101886 .

ZHANG B H , LOU S J , WANG L W , et al . Rethinking the expressive power of GNNs via graph biconnectivity‍ [C ] // International Conference on Learning Representations . Kigali : ACM , 2023 : 1 - 16 .

江兵兵 , 何文达 , 吴兴宇 , 等 . 基于自适应图学习的半监督特征选择 [J ] . 电子学报 , 2022 , 50 ( 7 ): 1643 - 1652 .

JIANG B B , HE W D , WU X Y , et al . Semi-supervised feature selection with adaptive graph learning [J ] . Acta Electronica Sinica , 2022 , 50 ( 7 ): 1643 - 1652 . (in Chinese)

ZHOU Z H , SUN Y Y , LI Y F . Multi-instance learning by treating instances as non-I.I.D. samples [C ] // Proceedings of the 26th Annual International Conference on Machine Learning . New York : ACM , 2009 : 1249 - 1256 .

WU J , ZHU X Q , ZHANG C Q , et al . Multi-instance multi-graph dual embedding learning [C ] // 2013 IEEE 13th International Conference on Data Mining . Piscataway : IEEE , 2013 : 827 - 836 .

WU J , ZHU X Q , ZHANG C Q , et al . Bag constrained structure pattern mining for multi-graph classification [J ] . IEEE Transactions on Knowledge and Data Engineering , 2014 , 26 ( 10 ): 2382 - 2396 .

PANG J , GU Y , XU J , et al . Parallel multi-graph classification using extreme learning machine and MapReduce‍ [J ] . Neurocomputing , 2017 , 261 : 171 - 183 .

ZHU Z X , ZHAO Y H . Multi-graph multi-label learning based on entropy [J ] . Entropy , 2018 , 20 ( 4 ): 245 .

HUANG M M , ZHAO Y H , WANG Y J , et al . Multi-graph multi-label learning with novel and missing labels‍ [J ] . Knowledge-Based Systems , 2023 , 276 : 110753 .

王兆慧 , 沈华伟 , 曹婍 , 等 . 图分类研究综述 [J ] . 软件学报 , 2022 , 33 ( 1 ): 171 - 192 .

WANG Z H , SHEN H W , CAO Q , et al . Survey on graph classification [J ] . Journal of Software , 2022 , 33 ( 1 ): 171 - 192 . (in Chinese)

KIPF T N , WELLING M . Semi-supervised classification with graph convolutional networks [EB/OL ] . ( 2016 )[2023 ] . http://arxiv.org/abs/1609.02907 http://arxiv.org/abs/1609.02907 .

TANG J , ZHANG J , YAO L M , et al . ArnetMiner: Extraction and mining of academic social networks [C ] // Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM , 2008 : 990 - 998 .

PERUSICH K , MCNEESE M D . Using fuzzy cognitive maps for knowledge management in a conflict environment [J ] . IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) , 2006 , 36 ( 6 ): 810 - 821 .

XU K , HU W , LESKOVER J , et al . How powerful are graph neural networks? [C ] // The 7th International Conference on Learning Representations . New Orleans : ACM , 2019 : 1 - 17 .

VELICKOVIC P , CUCURULL G , GASANOVA A , et al . Graph attention networks [C ] // The 6th International Conference on Learning Representations . Vancouver : ACM , 2018 : 1 - 12 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Anti-Noise Nonparallel Support Vector Machine with Margin Distribution

Large Scale Image Inpainting Based on Exemplar and Structure Information

Structural Fuzzy Twin Support Vector Machine with Pinball Loss

Related Author

LIU Li-ming

LI Ping

CHU Mao-xiang

CAI Hong-bin

WU Xiao-jun

LI Gong-qing

LI Kai

LI Hui

Related Institution

School of Electronic and Information Engineering， University of Science and Technology Liaoning

School of Mechanical Engineering and Automation, Harbing Institute of Technology.Shenzhen Graduate School

Shenzhen Key Lab for Advanced Motion Control and Modem Automation Equiprnents

School of Mechanical Engineering and Automation Harbing Institute of Technology.Shenzhen Graduate School Shenzhen Guangdong China

Shenzhen Key Lab for Advanced Motion Control and Modem Automation Equiprnents Shenzhen Guangdong China

⁰