Intelligent and Evolutionary Systems 2017

Invited Talk:

Title: Deep Learning for Graph Representation and its application to software defect identification.


Minh Le Nguyen

Associate Prof, Japan Advanced Institute of Science and Technology (JAIST),



[Abstract] In this talk, I will present our works on exploiting deep learning for graph representation and tree structure representation. We then show how our model can apply for analyzing source code, detecting existing defects in software components, and its application to malware detection. For analyzing source code, we will show how to exploit information of programs' abstract syntax trees instead of software metrics with deep learning models (i.e CNN and LSTM). Experimental results on the task of classifying 52000 programs into 104 target labels, showed that that the proposed methods dramatically achieve high performance in comparison with conventional methods.


Regarding the problem of identifying existing defects in software components, control flow graphs are constructed from the assembly instructions obtained by compiling source code; multi-view multi-layer directed graph-based convolutional neural networks (DGCNNs) is proposed to learn semantic features effectively. The experiments on four real-world datasets show that our method significantly outperforms the baselines including several other deep learning approaches.


[Biography] Minh Le Nguyen is currently an Associate Professor of School of Information Science, JAIST. He leads the lab on Machine Learning and Natural language Understanding at JAIST. He received his B.Sc. degree in information technology from Hanoi University of Science, and M.Sc. degree in information technology from Vietnam National University, Hanoi in 1998 and 2001, respectively. He received his Ph.D. degree in Information Science from School of Information Science, Japan Advanced Institute of Science and Technology (JAIST) in 2004. He was an assistant professor at School of information science, JAIST from 2008-2013. His research interests include machine learning, natural language understanding, question answering, text summarization, machine translation, big data mining, and Deep Learning.