Scholarlink

<p>Code search is a crucial task in software engineering, aiming to search relevant code from the codebase based on natural language queries. While deep-learning-based code search methods have demonstrated impressive performance, recent advances in contrastive learning have further enhanced the representation learning of these models. Despite these improvements, existing methods still have limitations in the representation learning of multi-modal data. Specifically, these methods suffer from a semantic loss in the representation learning of code and fail to explore functionally relevant code pairs in the representation learning fully. To address these limitations, we propose <i>A</i> <Emphasis Type="ItalicUnderline">R</Emphasis><i>epresentation</i> <Emphasis Type="ItalicUnderline">F</Emphasis><i>usion based</i> <Emphasis Type="ItalicUnderline">M</Emphasis><i>ulti-View Momentum</i> <Emphasis Type="ItalicUnderline">C</Emphasis><i>ontrastive Learning Framework for</i> <Emphasis Type="ItalicUnderline">C</Emphasis><i>ode</i> <Emphasis Type="ItalicUnderline">S</Emphasis><i>earch</i>, <i>named RFMC-CS</i>. <i>RFMC-CS</i> effectively retains the semantic and structural information of code through multi-modal representation and fusion. Through elaborately designed Multi-View Momentum Contrastive Learning, <i>RFMC-CS</i> can further learn the correlations between different modalities of samples and semantic relevant samples. The experimental results on the CodeSearchNet benchmark show that <i>RFMC-CS</i> outperforms seven advanced baselines on MRR and Recall@k metrics. The ablation experiments illustrate the effectiveness of each component. The portability experiments show that <i>RFMC-CS</i> has good portability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

RFMC-CS: a representation fusion based multi-view momentum contrastive learning framework for code search

  • 期刊论文

  • 发表日期：

    2025年1月27日

查看全文
  • Gong Chen,
  • Wenjie Liu,
  • Xiaoyuan Xie

摘要

Code search is a crucial task in software engineering, aiming to search relevant code from the codebase based on natural language queries. While deep-learning-based code search methods have demonstrated impressive performance, recent advances in contrastive learning have further enhanced the representation learning of these models. Despite these improvements, existing methods still have limitations in the representation learning of multi-modal data. Specifically, these methods suffer from a semantic loss in the representation learning of code and fail to explore functionally relevant code pairs in the representation learning fully. To address these limitations, we propose A Representation Fusion based Multi-View Momentum Contrastive Learning Framework for Code Search, named RFMC-CS. RFMC-CS effectively retains the semantic and structural information of code through multi-modal representation and fusion. Through elaborately designed Multi-View Momentum Contrastive Learning, RFMC-CS can further learn the correlations between different modalities of samples and semantic relevant samples. The experimental results on the CodeSearchNet benchmark show that RFMC-CS outperforms seven advanced baselines on MRR and Recall@k metrics. The ablation experiments illustrate the effectiveness of each component. The portability experiments show that RFMC-CS has good portability.