一句话：提出 TDPR，利用训练动态刻画测试输入的学习轨迹并用学习排序模型进行优先级排序，以低成本优先发现缺陷。
DNN 测试是保障深度神经网络质量的重要手段，但通常需要测试输入的真实标签，标注成本高。为解决该问题，本文提出基于训练动态的测试输入优先级排序技术 TDPR。其核心观察是：能揭示缺陷的样本与正常样本具有不同的学习轨迹。TDPR 为每个测试输入构建学习轨迹，刻画 DNN 在学习过程中不断演化的行为，并从中提取特征；随后应用 learning-to-rank 技术训练排序模型，智能地利用这些特征对测试输入排序。实验在 8 个不同测试输入领域、DNN 架构和输入类型的被测对象上开展，结果表明 TDPR 在测试输入优先级排序和指导 DNN 重训练两方面均优于 7 种基线方法。
Deep Neural Network (DNN) testing is one of the most widely-used techniques to guarantee the quality of DNNs. However, DNN testing typically requires the ground truth of test inputs, which is time-consuming and labor-intensive to obtain. To relieve the labeling-cost problem of DNN testing, we propose TDPR, a test input prioritization technique for DNNs based on training dynamics. The key insight of TDPR is that bug-revealing samples exhibit different learning trajectories compared to normal ones. Based on this, TDPR constructs a learning trajectory for each test input, which characterizes the evolving learning behavior of DNNs. Then, TDPR extracts features from these learning trajectories and applies learning-to-rank techniques to build a ranking model, which can intelligently utilize the generated features to prioritize test inputs. To evaluate TDPR, we conduct extensive experiments on 8 diverse subjects, considering various domains of test inputs, different DNN architectures, and diverse types of test inputs. The evaluation results demonstrate that TDPR outperforms 7 baseline approaches in both prioritizing test inputs and guiding the retraining of DNNs.CCS CONCEPTS• Software and its engineering → Software testing and debugging.