Substructure Assembling Network for Graph Classification

Authors

  • Xiaohan Zhao Snap Inc.
  • Bo Zong NEC Laboratories, America
  • Ziyu Guan Northwest University of China
  • Kai Zhang Temple University
  • Wei Zhao Xidian University

Keywords:

graph learning, graph representation learning, graph classification, deep graph neural network, deep learning

Abstract

Graphs are natural data structures adopted to represent real-world data of complex relationships. In recent years, a surge of interest has been received to build predictive models over graphs, with prominent examples in chemistry, computational biology, and social networks. The overwhelming complexity of graph space often makes it challenging to extract interpretable and discriminative structural features for classification tasks. In this work, we propose a novel neural network structure called Substructure Assembling Network (SAN) to extract graph features and improve the generalization performance of graph classification. The key innovation of our work is a unified substructure assembling unit, which is a variant of Recurrent Neural Network (RNN) designed to hierarchically assemble useful pieces of graph components so as to fabricate discriminative substructures. SAN adopts a sequential, probabilistic decision process, and therefore it can tune substructure features in a finer granularity. Meanwhile, the parameterized soft decisions can be continuously improved with supervised learning through back-propagation, leading to optimizable search trajectories. Overall, SAN embraces both the flexibility of combinatorial pattern search and the strong optimizability of deep learning, and delivers promising results as well as interpretable structural features in graph classification against state-of-the-art techniques.

Downloads

Published

2018-04-29

How to Cite

Zhao, X., Zong, B., Guan, Z., Zhang, K., & Zhao, W. (2018). Substructure Assembling Network for Graph Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11742