基于知识回放的即时软件缺陷预测增量模型  

Using knowledge replay for just-in-time software defectprediction incremental model

作　　者：张文静 李勇[1,2] 王越[1] Zhang Wenjing;Li Yong;Wang Yue(College of Computer Science&Technology,Xinjiang Normal University,Urümqi 830054,China;Key Laboratory of Safety-Critical Software of Ministry&Information Technology,Nanjing University of Aeronautics&Astronautics,Nanjing 211106,China)

机构地区：[1]新疆师范大学计算机科学技术学院,乌鲁木齐830054 [2]南京航空航天大学高安全系统的软件开发与验证技术工信部重点实验室,南京211106

出　　处：《计算机应用研究》2024年第11期3420-3425,共6页Application Research of Computers

基　　金：新疆维吾尔自治区自然科学基金资助项目(2022D01A225);国家自然科学基金资助项目(62241209);新疆师范大学研究生科研创新项目(XSY202301006)。

摘　　要：即时软件缺陷预测技术可以实现细粒度代码变更的即时缺陷预测,对于提高软件代码质量和保证软件可靠性具有重要意义。传统静态软件缺陷预测模型在处理即时软件数据流时会存在“知识遗忘”的情况,从而导致模型泛化性能较差的问题。为此,提出一种基于知识回放的即时软件缺陷预测增量模型方法。首先,通过知识回放机制存储模型参数和随机样本,实现对旧知识的学习;其次,使用分布式训练框架在本地设备上对即时软件数据流进行增量学习,通过重构实现模型的即时更新;最后采用知识蒸馏技术,构建全局增量预测模型。实验表明,该模型与常见模型算法相比,在保证训练效率的前提下,模型的综合性能表现较优。Just-in-time software defect prediction technology enables just-in-time defect prediction at the granularity of code changes,which is crucial for improving software code quality and ensuring software reliability.Traditional static software defect prediction models suffer from‘knowledge forgetting’when processing just-in-time software data streams,leading to poor model generalization performance.To address this,this paper proposed an incremental model method based on knowledge replay for just-in-time software defect prediction.Firstly,it used the knowledge replay mechanism stores model parameters and random samples to facilitate the learning of old knowledge.Secondly,this paper used a distributed training framework to perform incremental learning on just-in-time software data streams on local devices,achieving real-time model updates through restructuring.Lastly,this paper employed the knowledge distillation technique to construct a global incremental prediction mo-del.Experiments show that this model performs better in terms of comprehensive performance compared to common modeling algorithms while ensuring training efficiency.

关 键 词：即时软件缺陷预测 增量学习 知识回放 知识蒸馏 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]