KENN: Graph Kernel Neural Network Based on Linear Structural Entropy

被引：0
|
作者：
Xu L.-X. [1 ,2 ,3 ]
Xu W. [1 ]
Chen E.-H. [2 ,3 ]
Luo B. [4 ]
Tang Y.-Y. [5 ]
机构：
[1] School of Artificial Intelligence and Big Data, Hefei University, Hefei
[2] School of Computer Science and Technology, University of Science and Technology of China, Hefei
[3] State Key Laboratory of Cognitive Intelligence, Hefei
[4] School of Computer Science and Technology, Anhui University, Hefei
[5] Zhuhai UM Science & Technology Research Institute, University of Macau
来源：
Ruan Jian Xue Bao/Journal of Software | 2024年 / 35卷 / 05期
关键词：
graph classification; graph kernel; graph neural network (GNN); message passing aggregation; structural entropy;
D O I：
10.13328/j.cnki.jos.007039
中图分类号：
学科分类号：
摘要：
Graph neural network (GNN) is a framework for directly characterizing graph structured data by deep learning, and has caught increasing attention in recent years. However, the traditional GNN based on message passing aggregation (MP-GNN) ignores the smoothing speed of different nodes and aggregates the neighbor information indiscriminately, which is prone to the over-smoothing phenomenon. Thus, this study proposes a graph kernel neural network classification method KENN based on linear structural entropy. KENN firstly adopts the graph kernel method to encode node subgraph structure, determines isomorphism among subgraphs, and then utilizes the isomorphism coefficient to define the smoothing coefficient among different neighbors. Secondly, it extracts the graph structural information based on the low-complexity linear structural entropy to deepen and enrich the structural expression capability of the graph data. This study puts forward a graph kernel neural network classification method by deeply integrating linear structural entropy, graph kernel and GNN, which can solve the sparse node features of biomolecular data and information redundancy generated by leveraging node degree as features in social network data. It also enables the GNN to adaptively adjust its ability to characterize the graph structural features and makes GNN beyond the upper bound of MP-GNN (WL test). Finally, experiments on seven public graph classification datasets verify that the proposed model outperforms other benchmark models. © 2024 Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：2430 / 2445
页数：15
相关论文
共 44 条
  • [1] Ou MD, Cui P, Pei J, Zhang ZW, Zhu WW., Asymmetric transitivity preserving graph embedding, Proc. of the 22nd ACM SIGKDD Int’l Conf. on Knowledge Discovery and Data Mining, pp. 1105-1114, (2016)
  • [2] Xu LX, Bai L, Xiao J, Liu Q, Chen EH, Wang XF, Tang YY., Multiple graph kernel learning based on GMDH-type neural network, Information Fusion, 66, pp. 100-110, (2021)
  • [3] Bai L, Zhang ZH, Wang CY, Bai X, Hancock ER., A graph kernel based on the Jensen-Shannon representation alignment, Proc. of the 24th Int’l Conf. on Artificial Intelligence, pp. 3322-3328, (2015)
  • [4] Zhang XY, Zou JH, He KM, Sun J., Accelerating very deep convolutional networks for classification and detection, IEEE Trans. on Pattern Analysis and Machine Intelligence, 38, 10, pp. 1943-1955, (2016)
  • [5] Dong C, Loy CC, He KM, Tang XO., Image super-resolution using deep convolutional networks, IEEE Trans. on Pattern Analysis and Machine Intelligence, 38, 2, pp. 295-307, (2016)
  • [6] You JX, Ying R, Leskovec J., Position-aware graph neural networks, Proc. of the 36th Int’l Conf. on Machine Learning, pp. 7134-7143, (2019)
  • [7] Wijesinghe WOK, Wang Q., DFNets: Spectral CNNs for graphs with feedback-looped filters, Proc. of the 33rd Int’l Conf. on Neural Information Processing Systems, pp. 6009-6020, (2019)
  • [8] Bianchi FM, Grattarola D, Alippi C., Spectral clustering with graph neural networks for graph pooling, Proc. of the 37th Int’l Conf. on Machine Learning, pp. 874-883, (2020)
  • [9] Liu PJ, Li HY, Wang TY, Liu H, Sun LM, Ren YF, Li CP, Chen H., Multi-stage method for online vertical data partitioning based on spectral clustering, Ruan Jian Xue Bao/Journal of Software, 34, 6, pp. 2804-2832, (2023)
  • [10] Zhou CY, Zeng C, He P, Zhang Y., GKCI: An improved GNN-based key class identification method, Ruan Jian Xue Bao/Journal of Software, 34, 6, pp. 2509-2525, (2023)
12345