Prioritizing Test Inputs for DNNs Using Training Dynamics

Deep Neural Network (DNN) testing is one of the most widelyused 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.