Substructure Assembling Network for Graph Classification

By Xiaohan Zhao, Bo Zong, Ziyu Guan, Kai Zhang, Wei Zhao. 2018

28 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Materials Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ting-Li Chen
2. Yizhou Sun
3. Tingting Chen
4. Zhi-Li Zhang
5. Yang Qiao
6. Song Bian
7. Wei Wang
8. Haoyang Ding

In Computational Theory and Mathematics

1. Ting-Li Chen
2. Tingting Chen
3. Zhi-Li Zhang
4. Yang Qiao
5. Yizhou Sun
6. Wei Wang
7. Haoyang Ding
8. Saurabh Verma

In Materials Chemistry

1. Ting-Li Chen
2. Zhi-Li Zhang
3. Yizhou Sun
4. Saurabh Verma

Citations in the corpus

• Unsupervised Inductive Whole-Graph Embedding by Preserving Graph Proximity (2019, background): “, 2018), SAN (Zhao et al., 2018), DIFFPOOL (Ying et al.”
• SimGNN: A Neural Network Approach to Fast Graph Similarity Computation (2018, methodology): “However, once moving to the graph-level tasks, most existing works deal with the classification of a single graph [9, 14, 34, 44, 54, 57].”
• Graph Capsule Convolutional Neural Networks (2018, methodology): “Currently the most common method for achieving graph permutation invariance is performing aggregation (i.e., summing) over all graph node values (Atwood & Towsley, 2016; Dai et al., 2016; Zhao et al., 2018; Simonovsky & Komodakis, 2017).”