一句话：提出Coding-Fuse，通过证据理论定位各代码预训练模型的最优层并软投票融合，在提升SE分类性能的同时降低微调开销。
软件工程分类任务常依赖单个代码预训练模型（PTM），但不同PTM表现各异，简单融合多个PTM虽能提升性能，却会显著增加微调资源并降低效率。为此，作者提出Coding-Fuse框架：首先引入证据理论评估每个代码PTM各层输出特征与数据标签的适应性，定位潜在最优性能层；随后用软投票策略融合这些层的输出，得到新模型。实验在三个SE分类任务、两种任务场景下使用五个代码PTM，与完整PTM融合及原始单PTM比较。结果表明，Coding-Fuse能以更高效率和更少硬件资源取得优于完整融合的性能，并在同等效率和资源下优于单PTM，兼顾性能与绿色性。
Software engineering (SE) classification tasks play a vital role in improving software quality. Nevertheless, SE researchers and practitioners tend to rely on a single code pre-trained model (PTM) for downstream classification tasks. Previous studies have found that different code PTMs yield different performance in SE classification tasks, which triggers our thinking of whether the integration of multiple code PTMs improves the performance of classification tasks. Therefore, we first conduct preliminary exploratory research to analyze the impact of fusing multiple PTMs on code classification tasks. The result shows that compared to the single code PTM, the fusion of multiple code PTMs can improve the performance of SE classification tasks. However, the performance improvement also brings about the problem of increased finetuning resources and reduced application efficiency, which does not meet the greenness requirements. In order to address these issues, we propose Coding-Fuse, a framework of efficient fusion of code PTMs for SE classification tasks. Coding-Fuse first introduces evidence theory to evaluate the adaptability of the output features of each layer of code PTMs and data labels, and locates the potential best performance layer of different code PTMs. Then, Coding-Fuse uses a soft voting strategy to fuse the outputs of these layers to obtain a new model. We conduct experiments for effectiveness by comparing Coding-Fuse with the full PTM fusion method and the original single PTM using five different code PTMs on three different SE classification tasks and two task scenarios. The results show that Coding-Fuse can achieve better performance than the full PTM fusion method with higher efficiency and fewer hardware resources, and can achieve better performance than the original single PTM at the same efficiency and hardware resource level. We encourage SE practitioners to use our Coding-Fuse method in practice to fully utilize the advantages of each code PTM in the PTM repository according to task requirements to easily create new SE intelligent PTMs to achieve performance and greenness improvements.
DOI 原文 ·
@inproceedings{paperbot9466,
title = {Coding-Fuse: Efficient Fusion of Code Pre-Trained Models for Classification Tasks},
author = {Yu Zhao and Lina Gong and Zhiqiu Huang and Yuchen Jin and Mingqiang Wei},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00157}
}