Two-order Approximate Spectral Convolutional Model for Semi-Supervised Classification

被引：0
|
作者：
Gong P.-L. [1 ,2 ]
Ai L.-H. [1 ,2 ]
机构：
[1] School of Computer and Information Technology, Beijing Jiaotong University, Beijing
[2] Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing
来源：
Zidonghua Xuebao/Acta Automatica Sinica | 2021年 / 47卷 / 05期
基金：
中国国家自然科学基金;
关键词：
Graph theory; Node classification; Relational data; Semi-supervised learning; Spectral convolution;
D O I：
10.16383/j.aas.c200040
中图分类号：
学科分类号：
摘要：
In recent years, the spectral convolution method based on local first-order approximation has achieved significant advantages in semi-supervised node classification tasks. However, when updating the node feature representation at each stage, only the first-order neighbor node information is used, while the indirect neighbor node information is ignored. To this end, this paper combines Chebyshev' s truncated expansion and symmetric normalized Laplacian matrix, and by deducing and simplifying the two-order approximate spectral convolution module, an improved graph convolution model is proposed which fuses rich local structure information. A large number of experimental results show that the method proposed in this paper is superior to the existing popular methods on different datasets, which verifies the effectiveness of the model. Copyright © 2021 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：1067 / 1076
页数：9
相关论文
共 33 条
  • [1] Meng Z Q, Liang S S, Bao H Y, Zhang X L., Co-embedding attributed networks, Proceedings of the 12th ACM International Conference on Web Search and Data Mining, pp. 393-401, (2019)
  • [2] Kipf T N, Welling M., Semi-supervised classification with graph convolutional networks, Proceedings of the 5th International Conference on Learning Representations, pp. 1-14, (2017)
  • [3] Liu Z Q, Chen C C, Yang X X, Zhou J, Li X L, Song L., Heterogeneous graph neural networks for malicious account detection, Proceedings of the 27th International Conference on Information and Knowledge Management, pp. 2077-2085, (2018)
  • [4] Zhu X J, Ghahramani Z, Lafferty J D., Semi-supervised learning using Gaussian fields and harmonic functions, Proceedings of the 20th International Conference on Machine Learning, pp. 912-919, (2003)
  • [5] Talukdar P P, Crammer K., New regularized algorithms for transductive learning, Proceedings of the 2009 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, pp. 442-457, (2009)
  • [6] Belkin M, Niyogi P, Sindhwani V., Manifold regularization: A geometric framework for learning from labeled and unlabeled examples, Journal of Machine Learning Research, 7, 11, pp. 2399-2434, (2006)
  • [7] Weston J, Frederic R, Collobert R., Deep learning via semi-supervised embedding, Proceedings of the 25th International Conference on Machine Learning, pp. 639-655, (2012)
  • [8] Lu Q, Getoor L., Link-based classification, Proceedings of the 20th International Conference on Machine Learning, pp. 496-503, (2003)
  • [9] Perozzi B, Al-Rfou R, Skiena S., Deepwalk: Online learning of social representations, Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701-710, (2014)
  • [10] Tang J, Qu M, Wang M Z, Zhang M, Yan J, Mei Q Z., Line: Large-scale information network embedding, Proceedings of the 24th International Conference on World Wide Wed, pp. 1067-1077, (2015)
1234