Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning

2026-09-15

AI Summary

本文提出LWVIC4Code，一种非对比学习方法，通过跨层一致性正则化和深度依赖层加权来解决Type-IV代码克隆检测问题，提高了代码表示的鲁棒性和区分度。

Abstract

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.

Problem

• Type-IV Clones
• Semantic Equivalence
• Syntactic Differences
• Code Clone Detection

Innovation

• non-contrastive representation learning
• cross-layer consistency regularization
• depth-dependent layer weighting
• LWVIC4Code
• Type-IV clone detection