An Empirical Study on Data Distribution-Aware Test Selection for Deep Learning Enhancement

Qiang Hu, Yuejun Guo, Maxime Cordy, Xiaofei Xie, Lei Ma, Mike Papadakis, Yves Le Traon

Research output: Contribution to journalArticlepeer-review

18 Citations (Scopus)


Similar to traditional software that is constantly under evolution, deep neural networks need to evolve upon the rapid growth of test data for continuous enhancement (e.g., adapting to distribution shift in a new environment for deployment). However, it is labor intensive to manually label all of the collected test data. Test selection solves this problem by strategically choosing a small set to label. Via retraining with the selected set, deep neural networks will achieve competitive accuracy. Unfortunately, existing selection metrics involve three main limitations: (1) using different retraining processes, (2) ignoring data distribution shifts, and (3) being insufficiently evaluated. To fill this gap, we first conduct a systemically empirical study to reveal the impact of the retraining process and data distribution on model enhancement. Then based on our findings, we propose DAT, a novel distribution-aware test selection metric. Experimental results reveal that retraining using both the training and selected data outperforms using only the selected data. None of the selection metrics perform the best under various data distributions. By contrast, DAT effectively alleviates the impact of distribution shifts and outperforms the compared metrics by up to five times and 30.09% accuracy improvement for model enhancement on simulated and in-the-wild distribution shift scenarios, respectively.

Original languageEnglish
Article number78
JournalACM Transactions on Software Engineering and Methodology
Issue number4
Publication statusPublished - Jul 12 2022

All Science Journal Classification (ASJC) codes

  • Software


Dive into the research topics of 'An Empirical Study on Data Distribution-Aware Test Selection for Deep Learning Enhancement'. Together they form a unique fingerprint.

Cite this