DHAKR: Learning Deep Hierarchical Attention-Based Kernelized Representations for Graph Classification

Graph-based representations are powerful tools for analyzing structured data. In this paper, we propose a novel model to learn Deep Hierarchical Attention-based Kernelized Representations (DHAKR) for graph classification. To this end, we commence by learning an assignment matrix to hierarchically map the substructure invariants into a set of composite invariants, resulting in hierarchical kernelized representations for graphs. Moreover, we introduce the feature-channel attention mechanism to capture the interdependencies between different substructure invariants that will be converged into the composite invariants, addressing the shortcoming of discarding the importance of different substructures arising in most existing R-convolution graph kernels. We show that the proposed DHAKR model can adaptively compute the kernel-based similarity between graphs, identifying the common structural patterns over all graphs. Experiments demonstrate the effectiveness of the proposed DHAKR model.

Authors

• Feifei Qian School of Artificial Intelligence, and Engineering Research Center of Intelligent Technology and Educational Application, Ministry of Education, Beijing Normal University, Beijing, China
• Lu Bai School of Artificial Intelligence, and Engineering Research Center of Intelligent Technology and Educational Application, Ministry of Education, Beijing Normal University
• Lixin Cui School of Information, Central University of Finance and Economics, Beijing, China
• Ming Li
• Ziyu Lyu School of Cyber Science and Technology, Sun Yat-Sen University, Shenzhen, China
• Hangyuan Du School of Computer and Information Technology, Shanxi University, Taiyuan, China
• Edwin Hancock Department of Computer Science, University of York, York, United Kingdom

Keywords

No keywords are indexed for this paper.