Advanced Detection of Source Code Clones via an Ensemble of Unsupervised Similarity Measures

TL;DR

This paper presents an ensemble of unsupervised similarity measures for source code clone detection, achieving comparable results to transformer-based models on small datasets with lower training costs.

Contribution

It introduces a novel ensemble learning method combining multiple unsupervised similarity measures for code similarity assessment, especially effective on small datasets.

Findings

Ensemble approach performs well on small datasets.

Transformers like CodeBERT excel with large data.

Lower carbon footprint compared to training large models.

Abstract

The capability of accurately determining code similarity is crucial in many tasks related to software development. For example, it might be essential to identify code duplicates for performing software maintenance. This research introduces a novel ensemble learning approach for code similarity assessment, combining the strengths of multiple unsupervised similarity measures. The key idea is that the strengths of a diverse set of similarity measures can complement each other and mitigate individual weaknesses, leading to improved performance. Preliminary results show that while Transformers-based CodeBERT and its variant GraphCodeBERT are undoubtedly the best option in the presence of abundant training data, in the case of specific small datasets (up to 500 samples), our ensemble achieves similar results, without prejudice to the interpretability of the resulting solution, and with a much lower associated carbon footprint due to training. The source code of this novel approach can be downloaded from https://github.com/jorge-martinez-gil/ensemble-codesim.