Type-IV代码克隆检测：基于分层非对比表示学习

中文摘要 AI 辅助

软件克隆是彼此相似或功能等价的代码片段，它们对维护、重构和缺陷检测构成重大挑战。检测Type-IV克隆（语义等价但语法可能不同）对于传统的基于词法或语法的方法尤为困难。最近的机器学习方法依赖对比学习，这需要仔细的负采样且可能引入偏差。本文提出LWVIC4Code，一种专门为Type-IV克隆检测设计的非对比表示学习方法。基于方差-不变性-协方差正则化（VICReg）框架和先前的分层VICReg训练，LWVIC4Code引入了跨层一致性正则化和基于深度的层权重，以在Transformer各层间逐步细化语义信息，生成鲁棒且具有判别力的代码表示。我们进行了实证研究，将LWVIC4Code与对比学习基线及零样本大型语言模型在Python（Kamino）和多语言（GPTCloneBench）数据集上进行比较。结果表明，LWVIC4Code在无需负样本的情况下达到具有竞争力或更优的性能，受益于分层监督，并能有效地从Python泛化到其他语言，尤其是Java和C#。这些结果证明，非对比、分层的表示学习是鲁棒语义代码克隆检测的一个有前景的方向。

英文摘要

Software clones are fragments of code that are similar or functionally equivalent to each other. They pose significant challenges for maintenance, refactoring, and bug detection. Detecting Type-IV clones, which are semantically equivalent but may differ syntactically, is particularly difficult for traditional token- or syntax-based methods. Recent machine learning approaches rely on contrastive learning, which requires careful negative sampling and can introduce bias. In this paper, we propose LWVIC4Code, a non-contrastive representation learning approach specifically designed for Type-IV clone detection. Building on the Variance-Invariance-Covariance Regularization (VICReg) framework and prior layer-wise VICReg training, LWVIC4Code introduces cross-layer consistency regularization and depth-dependent layer weighting to progressively refine semantic information across transformer layers, producing robust and discriminative code representations. We conduct an empirical study comparing LWVIC4Code against a contrastive learning baseline and zero-shot large language models on Python (Kamino) and multi-language (GPTCloneBench) datasets. Results show that LWVIC4Code achieves competitive or superior performance without negative samples, benefits from layer-wise supervision, and generalizes effectively from Python to other languages, particularly Java and C#. These results demonstrate that non-contrastive, layer-wise representation learning is a promising direction for robust semantic code clone detection.

发表机构

• Université de Montréal（蒙特利尔大学）

机构由 AI 辅助整理，请以论文原文为准。