Journal
NEURAL NETWORKS
Volume 108, Issue -, Pages 533-543Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2018.09.001
Keywords
Labeled directed graphs; Convolutional neural networks (CNNs); Control flow graphs (CFGs); abstract syntax trees (ASTs)
Funding
- JSPS KAKENHI [JP15K16048]
Ask authors/readers for more resources
Exploiting graph-structured data has many real applications in domains including natural language semantics, programming language processing, and malware analysis. A variety of methods has been developed to deal with such data. However, learning graphs of large-scale, varying shapes and sizes is a big challenge for any method. In this paper, we propose a multi-view multi-layer convolutional neural network on labeled directed graphs (DGCNN), in which convolutional filters are designed flexibly to adapt to dynamic structures of local regions inside graphs. The advantages of DGCNN are that we do not need to align vertices between graphs, and that DGCNN can process large-scale dynamic graphs with hundred thousands of nodes. To verify the effectiveness of DGCNN, we conducted experiments on two tasks: malware analysis and software defect prediction. The results show that DGCNN outperforms the baselines, including several deep neural networks. (c) 2018 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available