Deep Learning Similarities from Different Representations of Source Code
MSR 2018 - 15th International Conference on Mining Software Repositories , May 28-29, 2018, Gothenburg, Sweden
Authors: Michele Tufano, Cody Watson, Gabriele Bavota, Massimiliano Di Penta, Martin White, and Denys Poshyvanyk
Abstract
Assessing the similarity between code components plays a pivotal role in a number of Software Engineering (SE) tasks, such as clone detection, impact analysis, refactoring, etc. Code similarity is generally measured by relying on manually defined or hand-crafted features (e.g., by analyzing the overlap among identifiers or comparing the Abstract Syntax Trees of two code components). These features represent a best guess at what SE researchers can utilize to exploit and reliably assess code similarity for a given task. Recent work has shown, when using a stream of identifiers to represent the code, that Deep Learning (DL) can effectively replace manual feature engineering for the task of clone detection. However, source code can be represented at different levels of abstraction: identifiers, Abstract Syntax Trees, Control Flow Graphs, and bytecode. We conjecture that each code representation can provide a different, yet orthogonal view of the same code fragment, thus, allowing a more reliable detection of similarities in code. In this paper, we demonstrate how SE tasks can benefit from a DL-based approach, which can automatically learn code similarities from different representations.
The online appendix is organized as follow:
Source code of the Deep Learning infrastructure.
Source code, binaries and origin of the two datasets employed in the Experimental Desing.
All the code representations extracted from the two datasets.
Research Questions
Data and results are available for each research question:
RQ1: How effective are different representations in detecting similar code fragments?
RQ2: What is the complementarity of different representations?
RQ3: How effective are combined multi-representation models?
RQ4: Are DL-based models applicable for detecting clones among different projects?
RQ5: Can trained DL-based models be reused on different, previously unseen projects?
All data available on Zenodo