Copy the page URI to the clipboard
Bui, Nghi D. Q.; Yu, Yijun and Jiang, Lingxiao
(2019).
Abstract
Despite being adopted in software engineering tasks, deep neural networks are treated mostly as a black box due to the difficulty in interpreting how the networks infer the outputs from the inputs. To address this problem, we propose AutoFocus, an automated approach for rating and visualizing the importance of input elements based on their effects on the outputs of the networks. The approach is built on our hypotheses that (1) attention mechanisms incorporated into neural networks can generate discriminative scores for various input elements and (2) the discriminative scores reflect the effects of input elements on the outputs of the networks. This paper verifies the hypotheses by applying AutoFocus on the task of algorithm classification (i.e., given a program source code as input, determine the algorithm implemented by the program). AutoFocus identifies and perturbs code elements in a program systematically, and quantifies the effects of the perturbed elements on the network’s classification results. Based on evaluation on more than 1000 programs for 10 different sorting algorithms, we observe that the attention scores are highly correlated to the effects of the perturbed code elements. Such a correlation provides a strong basis for the uses of attention scores to interpret the relations between code elements and the algorithm classification results of a neural network, and we believe that visualizing code elements in an input program ranked according to their attention scores can facilitate faster program comprehension with reduced code.
Viewing alternatives
Download history
Item Actions
Export
About
- Item ORO ID
- 66812
- Item Type
- Conference or Workshop Item
- Project Funding Details
-
Funded Project Name Project ID Funding Body Academic Research Fund (AcRF) Tier 1 grant from SIS at SMU Not Set Singapore Ministry of Education (MOE) SAUSE: Secure, Adaptive, Usable Software Engineering EP/R013144/1 (previous: EP/R005095/1) EPSRC (Engineering and Physical Sciences Research Council) Drone Identity No 783287 EU H2020 SESAR EngageKTN - Keywords
- attention mechanisms; neural networks; algorithm classification; interpretability; code perturbation; program comprehension
- Academic Unit or School
-
Faculty of Science, Technology, Engineering and Mathematics (STEM) > Computing and Communications
Faculty of Science, Technology, Engineering and Mathematics (STEM) - Research Group
- Centre for Research in Computing (CRC)
- Copyright Holders
- © 2019 ACM, © 2019 IEEE
- Depositing User
- Yijun Yu