不平衡图多尺度融合节点分类方法

doi:10.1007/s12204-022-2543-1

J Shanghai Jiaotong Univ Sci ›› 2024, Vol. 29 ›› Issue (3): 557-565.doi: 10.1007/s12204-022-2543-1

不平衡图多尺度融合节点分类方法

张静克1，何新林2，戚宗锋1，马超2，李建勋2

（1.电子信息系统复杂电磁环境效应国家重点实验室，河南洛阳471003；2. 上海交通大学电子信息与电气工程学院，上海200240）

收稿日期:2021-08-26 接受日期:2021-09-10 出版日期:2024-05-28 发布日期:2024-05-28

Unbalanced Graph Multi-Scale Fusion Node Classification Method

ZHANG Jingke¹ (张静克), HE Xinlin² (何新林), QI Zongfeng¹ (戚宗锋), MA Chao² (马超), LI Jianxun² (李建勋)

(1. State Key Laboratory of CEMEE, Luoyang 471003, Henan, China; 2. School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China)

Received:2021-08-26 Accepted:2021-09-10 Online:2024-05-28 Published:2024-05-28

摘要/Abstract

摘要： 图是一种描述事物间复杂关系的数据结构。基于图网络的节点分类方法在实际应用中有重要作用。现有的图节点分类方法均没有考虑节点标签分布不均衡的情况。本文针对不平衡图节点分布设计了有向图上的图卷积算法，实现基于多尺度融合图卷积网络的节点分类。该方法根据数据集上标签的不平衡性为每个类别设计了不同的传播深度，基于类别传播深度和图邻接矩阵在图卷积网络各层设计了不同的聚合函数，相对地扩大正样本的信息传播范围，从而提高不平衡图节点分类的准确性。最后在公开文本分类数据集上验证了算法的有效性。

关键词: 节点分类，不平衡学习，文本分类

Abstract: Graphs are used as a data structure to describe complex relationships between things. The node classification method based on graph network plays an important role in practical applications. None of the existing graph node classification methods consider the uneven distribution of node labels. In this paper, a graph convolution algorithm on a directed graph is designed for the distribution of unbalanced graph nodes to realize node classification based on multi-scale fusion graph convolution network. This method designs different propagation depths for each class according to the unbalance ratio on the data set, and different aggregation functions are designed at each layer of the graph convolutional network based on the class propagation depth and the graph adjacency matrix. The scope of information dissemination of positive samples is expanded relatively, thereby improving the accuracy of classification of unbalanced graph nodes. Finally, the effectiveness of the algorithm is verified through experiments on the public text classification datasets.

Key words: node classification, unbalanced learning, text classification

中图分类号:

TP391.1

张静克1，何新林2，戚宗锋1，马超2，李建勋2. 不平衡图多尺度融合节点分类方法[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(3): 557-565.

ZHANG Jingke¹ (张静克), HE Xinlin² (何新林), QI Zongfeng¹ (戚宗锋), MA Chao² (马超), LI Jianxun² (李建勋). Unbalanced Graph Multi-Scale Fusion Node Classification Method[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(3): 557-565.

参考文献

[1] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 779-788.
[2] LUONG T, PHAM H, MANNING C D. Effective approaches to attention-based neural machine translation [C]//2015 Conference on Empirical Methods in Natural Language Processing. Lisbon: ACL, 2015: 1412-1421.
[3] HINTON G, DENG L, YU D, et al. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups [J]. IEEE Signal Processing Magazine, 2012, 29(6): 82-97.
[4] YAN P, GAO J L. Research on Application of graph data mining in social networks [J]. Electronics World, 2016(8): 53-55 (in Chinese).
[5] FREEMAN L C. Visualizing social networks [M]//Social network data analytics. Boston: Springer, 2011: 307-326.
[6] THEOCHARIDIS A, VAN DONGEN S, ENRIGHT A J, et al. Network visualization and analysis of gene expression data using BioLayout Express3D [J]. Nature Protocols, 2009, 4(10): 1535-1550.
[7] SEN P, NAMATA G, BILGIC M, et al. Collective classification in network data [J]. AI Magazine, 2008, 29(3): 93.
[8] BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral networks and locally connected networks on graphs [DB/OL]. (2013-12-21). https://arxiv.org/abs/ 1312.6203.
[9] DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering [C]//30th Conference on Neural Information Processing Systems. Barcelona: NIPS, 2016: 3844-3852.
[10] KIPF T, WELLING M. Semi-supervised classification with graph convolutional networks [DB/OL]. (2016-09-09). https://arxiv.org/abs/1609.02907.
[11] ZHUANG C, MA Q. Dual graph convolutional networks for graph-based semisupervised classification [C]//2018 World Wide Web Conference. Lyon: In ternational World Wide Web Conference Committee, 2018: 499-508.
[12] ATWOOD J, TOWSLEY D. Diffusion-convolutional neural networks [C]//30th International Conference on Neural Information Processing Systems. Barcelona： NIPS, 2016: 2001-2009.
[13] HAMILTON W, YING Z, LESKOVEC J. Inductive representation learning on large graphs [C]//30th International Conference on Neural Information Processing Systems. Long Beach: NIPS, 2017: 1024-1034.
[14] VELIˇCKOVI′C P, CUCURULL G, CASANOVA A, et al. Graph attention networks [DB/OL]. (2017-10-30). https://arxiv.org/abs/1710.10903.
[15] JIANG W T, ZHANG C, ZHANG S C, et al. Multiscale feature map fusion algorithm for target detection [J]. Journal of Image and Graphics, 2019, 24(11): 1918-1931 (in Chinese).
[16] JOACHIMS T. Text categorization with Support Vector Machines: Learning with many relevant features [M]//Machine learning: ECML-98. Berlin, Heidelberg: Springer, 1998: 137-142.
[17] BLEI D M, NG A Y, JORDAN M I, et al. Latent Dirichlet allocation [J]. Journal of Machine Learning research, 2003, 3: 993-1022.
[18] KIM Y. Convolutional neural networks for sentence classification [C]//2014 Conference on Empirical Methods in Natural Language Processing. Doha: ACL, 2014: 1746-1751.
[19] LIU P F, QIU X P, HUANG X J. Recurrent neural network for text classification with multi-task learning [C]//Twenty-Fifth International Joint Conference on Artificial Intelligence. New York: AAAI Press, 2016: 2873-2879.
[20] JOULIN A, GRAVE E, BOJANOWSKI P, et al. Bag of tricks for efficient text classification [C]//15th Conference of the European Chapter of the Association for Computational Linguistic. Valencia: ACL, 2017: 427-431.
[21] YAO L, MAO C S, LUO Y. Graph convolutional networks for text classification [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33:7370-7377.

不平衡图多尺度融合节点分类方法

Unbalanced Graph Multi-Scale Fusion Node Classification Method

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价